Semantic Content Research Articles

Reading a graph is like reading a paragraph.

Vision provides rapid processing for some tasks, but encounters strong constraints from others. Although many tasks encounter a capacity limit of processing four visual objects at once, some evidence suggests far lower limits for processing relationships among objects. What is our capacity limit for relational processing? If it is indeed limited, then people may miss important relationships between data values in a graph. To test this question, we asked people to explore graphs of trivially simple 2 × 2 data sets and found that half of the viewers missed surprising and improbable relationships (e.g., a child's height decreasing over time). These relationships were spotted easily in a control condition, which implicitly directed viewers to prioritize inspecting the key relationships. Thus, a severe limit on relational processing, combined with a cascade of other capacity-limited operations (e.g., linking values to semantic content), makes understanding a graph more like slowly reading a paragraph then immediately recognizing an image. These results also highlight the practical importance of "data storytelling" techniques, where communicators design graphs that help their audience prioritize the most important relationships in data. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

“The Tragedy of Truth” in the Geography of Mikhail Prishvin’s Grove

This article examines the theme of the forest (“grove”) in the works and diaries of Mikhail Prishvin, which for him is inextricably linked not only to environmental problems, but also to the Russian people’s awareness of their historical path and destiny, to the understanding of the concept of “truth” and its semantic content in the minds of different people. The author compares Prishvin’s book of essays Berendey’s Grove (1935–1936), the fairytale Shiptimber Grove (1953) and the writer’s diaries, which reflect his impressions of his trip to Arkhangelsk region in 1935. On his journey to the north, Prishvin was not only carrying out the duties of the People’s Commissariat of the Timber Industry (supervising logging), but also trying to reach the precious and protected forest region – the “inviolable grove”, about which he heard many stories on his way. For Prishvin, the grove is an ideal place, untouched by the “axe of the Antichrist”. And this ideal mythological topos is all the more clearly contrasted with the terrible reality of deforestation that the writer saw and reflected on in his essays and diary. Even the virgin grove that the travellers reach near the Komi border turns out to be doomed. In Prishvin’s texts, conflicting ideas about the forest are not reconciled; he writes about poetic wood and round wood that should be felled. His last book, Shiptimber Grove, is dedicated to the Dream Grove, in which the author tries to save “his” fabulous grove. The article considers various options for the title of Prishvin’s final work, reflecting the movement of his creative consciousness. One of them is The Story of Truth or The Genuine Truth. The theme of truth, or the ‘tragedy’ of truth, is perhaps the central theme in Prishvin’s thought in later years, as well as in the works of a few of his contemporary writers; in the story, he entrusts the search for ‘truth’ to his characters. The shiptimber grove, protected by the Komi people and invaded by war, becomes a multiple image and symbol in the book, including a symbol of truth, uniting the general and the personal, the natural and the human, the past and the future.

Language models, like humans, show content effects on reasoning tasks.

reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks but exhibit many imperfections. However, human abstract reasoning is also imperfect. Human reasoning is affected by our real-world knowledge and beliefs, and shows notable "content effects"; humans reason more reliably when the semantic content of a problem supports the correct logical inferences. These content-entangled reasoning patterns are central to debates about the fundamental nature of human intelligence. Here, we investigate whether language models-whose prior expectations capture some aspects of human knowledge-similarly mix content into their answers to logic problems. We explored this question across three logical reasoning tasks: natural language inference, judging the logical validity of syllogisms, and the Wason selection task. We evaluate state of the art LMs, as well as humans, and find that the LMs reflect many of the same qualitative human patterns on these tasks-like humans, models answer more accurately when the semantic content of a task supports the logical inferences. These parallels are reflected in accuracy patterns, and in some lower-level features like the relationship between LM confidence over possible answers and human response times. However, in some cases the humans and models behave differently-particularly on the Wason task, where humans perform much worse than large models, and exhibit a distinct error pattern. Our findings have implications for understanding possible contributors to these human cognitive effects, as well as the factors that influence language model performance.

STUDY OF NONVERBAL COMMUNICATION OF CONFERENCE INTERPRETERS’ LINGUISTIC PERSONALITY

The article is devoted to the relevance and significance of nonverbal communication in a comprehensive approach to the study of the linguistic personality of a conference interpreter. The author explains the use of the communicative-functional approach to the analysis of verbal and nonverbal behaviour of the interpreter’s linguistic personality. The hypothesis of the study brings out that the nonverbal behaviour of the interpreter’s linguistic personality is determined by the content of the translated utterance, the interpreter’s internal motivation and intention (the pragmatic level of the linguistic personality), and it is consistently proved that nonverbal means shall be considered as part of the structural model of the linguistic personality, influencing the verbal representation of the linguistic personality. The author analyses a nonverbal sign (at its beginning, middle and end of its expression) and a translation syntagm as minimal units of study. The units of the study were collected by solid sampling from 14 video recordings of interpretation series, total study includes 105 minutes with records of nonverbal signs used by linguistic personality the interpreters participated in the study. As a result, the author classified nonverbal signs into vegetatives and somatives, and she structurally described the content of the groups of kinesic somatives, oculesic somatives and prosodic somatives, presenting the semantic content of nonverbal signs; within kinesic somatives, the author described a subgroup of comfort-gestures. The paper concludes about the prospect of further study of nonverbal communication and its importance for the study of linguistic personality in general.

DREAM MOTIF IN VLADISLAV KHODASEVICH’S POETRY COLLECTION “EUROPEAN NIGHT”

The article describes the semantic content and poetics of the dream motif present in Vladislav Khodasevich’s collection “European Night”, and we form our own concept of “inspiration”. It is shown that the dream leitmotif characterises the psychological state of the lyrical hero associated with the arrival or absence of creative inspiration. The semantics of the motif is implemented antinomically. On the one hand, the dream-inspiration saves the lyrical hero from the mundane routine. On the other hand, ordinary earthly life in some poems appears to the lyrical subject as a dream-obsession. The story of this dream-obsession gets a particularly tragic sound in the context of the collection. The expanded metaphor “European Night” in the author’s incarnation reinforces two intentions – obsession dream and salvation dream are opposed. In the lyrical space of Vladislav Khodasevich’s “European Night”, dream becomes a metaphor for a special borderline state, instilled and even “imposed” from the outside on the creator hero. According to the poet’s artistic philosophy, inspiration, being the result of the mobilisation of all word artist’s abilities, is an “otherworldly” being sent from above, leading to greater creative productivity. The “dream” motif in the contradictory context of the above-mentioned poems of “European Night” indicates the salvation function of inspiration, which allows the creator to get rid of the “earthly dream”, to spiritually “see through” and to lead people.

Інтерпретація авторського «Я» крізь призму епістолярного дискурсу Ольги Кобилянської

The paper highlights the postulates of personal discourse theories (egotext) designed for the aspectual clarification of Olha Kobylianska’s epistolary discourse originality. The strokes of the writer’s biography are analyzed via the prism of her self-awareness concerning individual preferences, passions, and aspirations, in particular with an indication of the incomplete life potential realization (loneliness is critically evaluated), the presentation of the philosopher’s key worldviews, primarily feminist (gender) beliefs, and the understanding of her own creative potential national-genetic basics. It is demonstrated how O. Kobylianska expresses her views on the environment, religion, mysticism, psychology, and shows her love for learning and mastering Polish and German as foreign languages; her artistic writing in general, the tendency to intuitive prediction reflections, and her interest in music and theater are also discussed in the piece of research. The artist sincerely admits that her emotions are not always controlled during the creative process, as well as in real-life situations. In the writer’s epistolary thesaurus, one can trace the vocabulary and phraseology frequency to indicate certain psychological states and emotions, which proves that in O. Kobylianska’s nature are high sensuality, emotionality, and expressiveness. The artist’s epistolary behavior features (politeness,self-irony, humorous tone, benevolence and emotionality) display her epistolary idiostyle originality, indicating a distinct soul sensitivity. The lexeme soul has a high frequency in the text of the considered letters and presents powerful semantic and pragmatic content. O. Kobylianska’s letters analysis makes it possible to claim that she is a talented writer, an introverted type of thinking individual, a born psychologist, as well as a connoisseur of Ukrainian and other linguistic cultures.

Гуманитарные и социальные науки: теоретико-познавательные основания

Scientific natural science, which had been established in European culture since the mid-17th century, began to transmit samples of scientific knowledge into the field of studying social reality. Until the 19th century, the only mental form of reflecting this reality was “primary history,” as Hegel defined it, i.e. tradition of historiography coming from Herodotus. This tradition received its design, oriented towards the field of scientific rationality, from the German historian Leopold von Ranke: to show “how it really was” (wie es eigentlich gewesen). Its social function is the formation of national historical memory. But methodological reflection at the turn of the 19th and 20th centuries revealed, as it seemed to it, two radical differences between “primary history” and other “sciences of culture” from natural science. In this regard, the categories of “values” and “understanding” were emphasized. The presence of these categories in the foundations of any science determines its specification as a humanitarian science. The first attempts to transfer certain aspects of the disciplinary matrices of natural science to the sphere of social science are associated with the names of Kant and Marx. Both attempts were unsuccessful. But, unlike Kant’s, the “materialist understanding of history” found its supporters and successors. Its main error is the unlawful direct transfer of the semantic content of the category “matter”, as it developed in natural science (the relationships of things), to the relationships between people endowed with consciousness. The addressee of social sciences are cultural forms, the existence of which has an objective status of existence, but relative to the individual consciousness of acting people. These are, for example, social institutions. The humanities deal with meanings, the existence of which is determined by systems of social communications.

Методология гармонической конвергенции для мировоззрения универсализма

Introduction. The article is devoted to methodological issues of the formation of the worldview of universalism, excluding the reduction of the one, the whole, many and a part to each other. Limited, one-sided types of worldviews of holism, merism and the genological type allow such a reduction, excluding the choice of optimal, sustainable co-development of nature, society and a man. Theoretical analysis. A comparative analysis of the ideological and methodological attitudes of holism, merism and onecentrism is carried out in order to identify their reductionist extremes. As their replacement, the author proposes a new version of the worldview of universalism (postholism), formed by methodological means that exclude the absolutization of a one, whole or parts. The main means of such kind are the concept of a «one whole in a single part», the procedure of «harmonic convergence» and the principle of «non-reductionism», which ensure a tendency to fusion of the semantic content of the concepts of a one, whole, singular, and unique. Conclusion. The conclusion is made that, thanks to these tools, the worldview of postholism is able to neutralize the methodological flaws of holism, mechanicism, elementarism, individualism, henotheism, and other ideological and methodological platforms. This allows for a proportionate interaction in the course of the development of a one (fundamental laws of being), a whole (society) and a part (person).

Integrity of autobiographical memory and episodic future thinking in older adults varies with cognitive functioning

Research has documented changes in autobiographical memory and episodic future thinking in mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, cognitive decline occurs gradually and recent findings suggest that subtle alterations in autobiographical cognition may be evident earlier in the trajectory towards dementia, before AD-related symptoms emerge or a clinical diagnosis has been given. The current study used the Autobiographical Interview to examine the episodic and semantic content of autobiographical past and future events generated by older adults (N = 38) of varying cognitive functioning who were grouped into High (N = 20) and Low Cognition (N = 18) groups based on their Montreal Cognitive Assessment (MoCA) scores. Participants described 12 past and 12 future autobiographical events, and transcripts were scored to quantify the numbers of internal (episodic) or external (non-episodic, including semantic) details. Although the Low Cognition group exhibited a differential reduction for internal details comprising both past and future events, they did not show the expected overproduction of external details relative to the High Cognition group. Multilevel modelling demonstrated that on trials lower in episodic content, semantic content was significantly increased in both groups. Although suggestive of a compensatory mechanism, the magnitude of this inverse relationship did not differ across groups or interact with MoCA scores. This finding indicates that external detail production may be underpinned by mechanisms not affected by cognitive decline, such as narrative style and the ability to contextualize one's past and future events in relation to broader autobiographical knowledge.

ESSENCE AND STRUCTURE OF AN OATH OF LAW

Essence and structural organization of oath in legal aspect was studied. Oath as personal solemn con rmation by religious and non-religious act is considered, which was used as an element of jurisprudence in the past and is currently relevant. The structural organization of the oath is presented by analogy with the construction adopted in the normative legal theory. Modern using of oath highlights the relevance of topic. It is noted that structure of oath has practically not undergone signi cant changes from ancient until now. Oath breaking as basis of punishment is considered. Psychic and emotional side of oath is considered. As an illustration of the semantic content of oaths, excerpts from literary works of ancient Greek authors are given. Taking the oath according the topic imply legal aspect of activity by persons and authority. Publicity of the swornin ceremony is indicated. An original version of structuring of the oath is proposed. The sources of the research are original written documents, as well as translations with comments, fragments that have come down to us or intact petroglyphs located in archaeological parks or museums. The deductive, inductive, historical- linguistic, formallegal methods along with description, analysis and synthesis, and non-stationary research were used.

The interrelation of motor and mental actions in the process of formation of social competitiveness of a personality

Introduction. The work is devoted to the study of the peculiarities of the formation of competitiveness in the process of physical education classes. The psychological features of purposeful formation of competitiveness are considered. The positive relationship between specially organized motor actions and the formed competitiveness of students has been practically proved and theoretically substantiated.Materials and Methods. To solve the research tasks, the semantic content of the basic concepts characterizing competitiveness was determined. The semantic analysis of the presented concepts was carried out according to the dictionary of the Russian language edited by A. P. Evgenieva. The definition of the semantic core of concepts was carried out by the content analysis method proposed by S. A. Gaponova. Semantic, basic units of textual information were identified. The semantic core, the fundamental feature of a text or concept, was determined.Results. We have established that the semantic core of all manifestations of competitiveness, without exception, is overcoming. It is proved that overcoming various external (physical) and internal (mental) barriers is a necessary and sufficient condition for the formation of competitiveness. It is argued that specially organized motor activity makes it possible to purposefully form competitiveness.Discussion and conclusions. The factors and conditions affecting the process of competitiveness formation are discussed. The basic feature of competitiveness has been established in previously conducted in-house scientific research. This process is analyzed from the perspective of the theory of the gradual formation of mental actions and concepts (P. Ya. Galperin), as well as the levels of movement control (N. A. Bernstein). The presented material is the theoretical basis for the creation of a methodology for the purposeful formation of competitiveness among students.

Prior semantic-embedding representation learning for on-the-fly FG-SBIR

In fine-grained sketch-based image retrieval (FG-SBIR) framework, sketch drawing is a time-consuming and skill-intensive process that greatly restricts its practical application. Our study aims to enhance the early-stage retrieval efficiency by utilizing partial sketches with a minimum number of strokes in the on-the-fly FG-SBIR framework. Nevertheless, partial sketches with few strokes usually lack global information and consist only of sparse local details. This lack of detail results in ambiguous semantic content and indistinct differences among images, which consequently impairs early-stage retrieval. To acquire an efficient representation for these sketches, we propose a multi-granularity feature representation model that utilizes prior knowledge embedding to deal with the sketch drawing process. In the first stage,we design a triplet network to learn the joint a coarse representation embedding space that is common between the complete sketch and the image. In the second stage, We enhanced the semantic representation of sketches by utilizing prior knowledge, which aids in supplementing missing fine-grained features. This was achieved by formalizing the prior knowledge and integrating it into the feature vector obtained in the initial stage, thereby acquiring the final representation of a subset of sketches. Experiments conducted on two public datasets indicate that our method outperforms the state-of-the-art baseline during the early retrieval phase. In practical applications, our approach has also achieved good results.

Improving equity in diabetes technology use: Voices of youth and their parents.

There are marked inequities in clinical outcomes and rates of diabetes technology use among youth with type 1 diabetes (T1D). The quantitative data from our mixed methods cohort study identified significant improvements in glycaemia and quality of life in participants. We aimed to use qualitative methods to provide further insight into our quantitative findings in the setting of underlying health disparities. Fifteen publicly insured, insulin pump-naïve non-Hispanic Black youth aged 6-21 years with T1D and baseline haemoglobin A1c (HbA1c) ≥86 mmol/mol (10%) and their parents participated in a mixed methods cohort study. Semi-structured interviews were conducted separately with parents and youth after completion of 6 months of HCL use. Three topic areas were explored: (1) Experience using HCL, (2) barriers to HCL and (3) facilitators to accessing HCL. Semantic content analysis and consensus coding involving two team members were used to generate themes. Thematic saturation was achieved. Youth (Medianage 14.9 years, 67% female) and parents (92% female) were interviewed. Youth and their parents reported that access to HCL provides a new outlook on living with T1D, although managing T1D is still hard. They felt that diabetes technology is most helpful for those struggling with management. Participants experienced barriers to access including misconceptions of HCL systems, clinician bias and systemic racism. They suggested these barriers can be overcome by offering diabetes technology education for all people with T1D, increasing awareness of HCL in the community and providing resources to overcome barriers created by social determinants of health. The voices of historically minoritised youth with suboptimal T1D control and their parents provide important, previously unreported experiences and perspectives on barriers and facilitators to using HCL that will shape interventions to improve equity in access to diabetes technology.

Fidelity based visual compensation and salient information rectification for infrared and visible image fusion

The fusion technology, combining infrared and visible modes, has the potential to enhance the semantic content of backgrounds, thereby improving scene interpretability. However, most existing image fusion algorithms primarily concentrate on the fusion process, often neglecting the importance of preprocessing the source images to enhance their visual fidelity. Additionally, these algorithms frequently overlook the distinct characteristics of infrared and visible modes, leading to suboptimal weight allocations that do not correspond with human perception. To tackle these issues, this paper proposes a fusion algorithm that emphasizes visual fidelity and the rectification of salient information. More specifically, we improve fusion algorithms by designing an adaptive enhancement method based on Taylor approximation and visual compensation, which proves particularly effective in complex environments. Our proposed multi-scale decomposition approach extracts salient information from the transmission map, thereby enriching fusion results with finer details to accentuate target features. Drawing inspiration from the distinctive attributes of infrared and visible image modes, we devise a fusion weight calculation method grounded in similarity measurements to effectively convey significant information from the source images. To validate the effectiveness of our proposed method, we conducted validation experiments using publicly available datasets. Our experimental findings exhibit a prominent advantage over fifteen state-of-the-art fusion algorithms in both subjective and objective assessments. Our code is publicly available at: https://github.com/VCMHE/FVC_SIR.

КОНЦЕПТУАЛЬНЫЕ ПОНЯТИЯ В НАЦИОНАЛЬНОЙ ЯЗЫКОВОЙ КАРТИНЕ МИРА КАЗАХОВ (НА МАТЕРИАЛЕ ПОЭЗИИ ЖЫРАУ)

The study of texts by Kazakh zhyrau with the aim of identifying the peculiarities of conceptualizing universals of objective reality within the framework of Kazakh culture undoubtedly presents a significant interest for linguacultural researchers and ethnolinguists. The analysis of such material can provide valuable information about the structure and semantic content of nationally specific concepts. The study proves the interrelation of the concepts considered in the article, expands the idea of the whole conceptual system of Kazakh literature. The authors examined a series of universal concepts reflected in the poetic works of zhyraus, transformed by the worldview and understanding of the world of the Kazakh people, and became foundational elements of the national conceptual sphere. The research employed methods such as descriptive analysis, statistical analysis to identify the frequency of usage of certain words, and conceptual analysis to extract cognitive models. The results obtained during the analysis serve as a key to unlocking the culture, history, and mentality of the Kazakh ethnic group. The aim of the article is to study conceptual notions in the national language worldview of Kazakhs, related to representations of life and death, homeland, family, and other significant concepts in Kazakh linguaculture. The material for the study consisted of texts of zhyraus` poetry, as well as Kazakh proverbs and sayings. The considered problem is relevant in terms of studying the language of Kazakh poetry as a means of comprehending ethnic mentality

Communication, Manipulation, Seduction. The Pragmatics of Transparency

Communicative interaction is never totally transparent. A definition in terms of pure information transfer constitutes an impoverishment of the semantic content of a message. Other emotional connotations of linguistic interaction are deeply rooted in the depths of the subjects' psychology. This means that interaction is often manipulative and even seductive. This article attempts to present more systematically the conditions of manipulative and seductive discursive production. Speech act theory (Austin, Searle) and conversational logic (Grice) offer some tools to more or less formalize these subtle conditions of production of non-transparent “communication”.

MMAIndoor: Patched MLP and multi-dimensional cross attention based self-supervised indoor depth estimation

Depth estimation can provide auxiliary information for scene perception. Generally, extensive textureless surfaces, such as walls and ceilings, exist in indoor environments, and they share similar scene and semantic content. Overly consistent features of local textureless areas fail to reflect changes in depth information, thus degrading the performance of existing depth estimation methods. In response to this challenge, we propose a special indoor depth estimation method, named as MMAIndoor, which can provide global semantic guidance and shape priors for local textureless depth estimation. The depth estimation network is designed efficiently, encompassing the initial convolutional stage and the latent patched multi-layer perceptron (Pat-MLP) stage. The novel Pat-MLP block utilizes MLP partitioning to globally model depth-local information from the convolutional stage and it incorporate axial shift operations to extract local information from various spatial locations, suppressing the smoothing effect of MLP and improving precise estimation of sharp depth changes or small structures indoors. Further, we build a multi-dimensional cross attention (MCA) module to address the weak correlation of the current residual connections for the global context. This MCA captures global dependencies across multi-dimensions by sequentially executing cross attention on both channels and spatial, and effectively mitigate semantic gaps in residual connections. Sufficient experimental results demonstrate the state-of-the-art performance of MMAIndoor on benchmark datasets including NYUv2, ScanNet, and InteriorNet.

Effects of conflicting emotional cues on toddlers' emotion perception.

The communication of emotion is dynamic and occurs across multiple channels, such as facial expression and tone of voice. When cues are in conflict, interpreting emotion can become challenging. Here, we examined the effects of incongruent emotional cues on toddlers' interpretation of emotions. We presented 33 children (22-26 months, Mage = 23.8 months, 15 female) with side-by-side images of faces along with sentences spoken in a tone of voice that conflicted with semantic content. One of the two faces matched the emotional tone of the audio, whereas the other matched the semantic content. For both congruent and incongruent trials, toddlers showed no overall looking preference to either type of face stimuli. However, during the second exposure to the sentences of incongruent trials, older children tended to look longer to the face matching semantic content when listening to happy vs. angry content. Results inform our understanding of the early development of complex emotion understanding.

The Language Network Reliably "Tracks" Naturalistic Meaningful Nonverbal Stimuli.

The language network, comprised of brain regions in the left frontal and temporal cortex, responds robustly and reliably during language comprehension but shows little or no response during many nonlinguistic cognitive tasks (e.g., Fedorenko & Blank, 2020). However, one domain whose relationship with language remains debated is semantics-our conceptual knowledge of the world. Given that the language network responds strongly to meaningful linguistic stimuli, could some of this response be driven by the presence of rich conceptual representations encoded in linguistic inputs? In this study, we used a naturalistic cognition paradigm to test whether the cognitive and neural resources that are responsible for language processing are also recruited for processing semantically rich nonverbal stimuli. To do so, we measured BOLD responses to a set of ∼5-minute-long video and audio clips that consisted of meaningful event sequences but did not contain any linguistic content. We then used the intersubject correlation (ISC) approach (Hasson et al., 2004) to examine the extent to which the language network "tracks" these stimuli, that is, exhibits stimulus-related variation. Across all the regions of the language network, meaningful nonverbal stimuli elicited reliable ISCs. These ISCs were higher than the ISCs elicited by semantically impoverished nonverbal stimuli (e.g., a music clip), but substantially lower than the ISCs elicited by linguistic stimuli. Our results complement earlier findings from controlled experiments (e.g., Ivanova et al., 2021) in providing further evidence that the language network shows some sensitivity to semantic content in nonverbal stimuli.

BPJDet: Extended Object Representation for Generic Body-Part Joint Detection.

Detection of human body and its parts has been intensively studied. However, most of CNNs-based detectors are trained independently, making it difficult to associate detected parts with body. In this paper, we focus on the joint detection of human body and its parts. Specifically, we propose a novel extended object representation integrating center-offsets of body parts, and construct an end-to-end generic Body-Part Joint Detector (BPJDet). In this way, body-part associations are neatly embedded in a unified representation containing both semantic and geometric contents. Therefore, we can optimize multi-loss to tackle multi-tasks synergistically. Moreover, this representation is suitable for anchor-based and anchor-free detectors. BPJDet does not suffer from error-prone post matching, and keeps a better trade-off between speed and accuracy. Furthermore, BPJDet can be generalized to detect body-part or body-parts of either human or quadruped animals. To verify the superiority of BPJDet, we conduct experiments on datasets of body-part (CityPersons, CrowdHuman and BodyHands) and body-parts (COCOHumanParts and Animals5C). While keeping high detection accuracy, BPJDet achieves state-of-the-art association performance on all datasets. Besides, we show benefits of advanced body-part association capability by improving performance of two representative downstream applications: accurate crowd head detection and hand contact estimation.