Moments In Videos Research Articles

Unsupervised Video Moment Retrieval with Knowledge-based Pseudo Supervision Construction

Video moment retrieval locates a specified moment by a sentence query. Recent approaches have made remarkable advancements with large-scale video-sentence annotations. These annotations require extensive human labor and expertise, leading to the need for unsupervised fashion. Generating pseudo-supervision from videos is an effective strategy. With the power of the large-scale pre-trained model, we introduce knowledge into constructing pseudo-supervision. The main technical challenge is improving pseudo-supervision diversity and alleviating noise brought by external knowledge. To address these problems, we propose two Knowledge-based Pseudo Supervision Construction (KPSC) strategies: KPSC-P and KPSC-F. They all follow two steps: generating diverse samples and alleviating knowledge chaos. The main difference is that the former first learns a representation space with prompt tuning, while the latter directly utilizes data information. KPSC-P has two modules: 1) Proposal Prompt (PP): Generate temporal proposals; 2) Verb Prompt (VP): Generate pseudo-queries with noun-verb patterns. KPSC-F also has two modules: 1) Captioner: Generating candidate queries; 2) Filter: Alleviating knowledge chaos. Thus, our KPSC involves two attempts to extract knowledge from pre-trained models. Extensive experiments show that our attempts outperform the existing unsupervised methods on two public datasets (Charades-STA and ActivityNet-Captions) and perform on par with several methods using stronger supervision.

SketchQL: Video Moment Querying with a Visual Query Interface

Localizing video moments based on the movement patterns of objects is an important task in video analytics. Existing video analytics systems offer two types of querying interfaces based on natural language and SQL, respectively. However, both types of interfaces have major limitations. SQL-based systems require high query specification time, whereas natural language-based systems require large training datasets to achieve satisfactory retrieval accuracy. To address these limitations, we present SketchQL, a video database management system (VDBMS) for offline, exploratory video moment retrieval that is both easy to use and generalizes well across multiple video moment datasets. To improve ease-of-use, SketchQL features a visual query interface that enables users to sketch complex visual queries through intuitive drag-and-drop actions. To improve generalizability, SketchQL operates on object-tracking primitives that are reliably extracted across various datasets using pre-trained models. We present a learned similarity search algorithm for retrieving video moments closely matching the user's visual query based on object trajectories. SketchQL trains the model on a diverse dataset generated with a novel simulator, that enhances its accuracy across a wide array of datasets and queries. We evaluate SketchQL on four real-world datasets with nine queries, demonstrating its superior usability and retrieval accuracy over state-of-the-art VDBMSs.

Modality-Aware Heterogeneous Graph for Joint Video Moment Retrieval and Highlight Detection

Modality-Aware Heterogeneous Graph for Joint Video Moment Retrieval and Highlight Detection

Triadic temporal-semantic alignment for weakly-supervised video moment retrieval

Video Moment Retrieval (VMR) aims to identify specific event moments within untrimmed videos based on natural language queries. Existing VMR methods have been criticized for relying heavily on moment annotation bias rather than true multi-modal alignment reasoning. Weakly supervised VMR approaches inherently overcome this issue by training without precise temporal location information. However, they struggle with fine-grained semantic alignment and often yield multiple speculative predictions with prolonged video spans. In this paper, we take a step forward in the context of weakly supervised VMR by proposing a triadic temporal-semantic alignment model. Our proposed approach augments weak supervision by comprehensively addressing the multi-modal semantic alignment between query sentences and videos from both fine-grained and coarse-grained perspectives. To capture fine-grained cross-modal semantic correlations, we introduce a concept-aspect alignment strategy that leverages nouns to select relevant video clips. Additionally, an action-aspect alignment strategy with verbs is employed to capture temporal information. Furthermore, we propose an event-aspect alignment strategy that focuses on event information within coarse-grained video clips, thus mitigating the tendency towards long video span predictions during coarse-grained cross-modal semantic alignment. Extensive experiments conducted on the Charades-CD and ActivityNet-CD datasets demonstrate the superior performance of our proposed method.

Stacked collaborative transformer network with contrastive learning for video moment localization

Video grounding intends to perform temporal localization in multimedia information retrieval. The temporal bounds of the target video span are determined for the given input query. A novel interactive multi-head self-attention (IMSA) transformer is proposed to localize an unseen moment in the untrimmed video for the given image. A new semantic-trained self-supervised approach is considered in this paper to perform cross-domain learning to match the image query – video segment. It normalizes the convolution function enabling efficient correlation and collecting of semantically related video segments across time based on the image query. A double hostile Contrastive learning with Gaussian distribution parameters method is advanced to learn the representations of video. The proposed approach performs dynamically on various video components to achieve exact semantic synchronization and localization among queries and video. In the proposed approach, the IMSA model localizes frames greatly compared to other approaches. Experiments on benchmark datasets show that the proposed model can significantly increase temporal grounding accuracy. The moment occurrence is identified in the video with a start and end boundary ascertains an average recall of 86.45% and a mAP of 59.3%.

Video Moment Retrieval With Noisy Labels.

Video moment retrieval (VMR) aims to localize the target moment in an untrimmed video according to the given nature language query. The existing algorithms typically rely on clean annotations to train their models. However, making annotations by human labors may introduce much noise. Thus, the video moment retrieval models will not be well trained in practice. In this article, we present a simple yet effective video moment retrieval framework via bottom-up schema, which is in end-to-end manners and robust to noisy label training. Specifically, we extract the multimodal features by syntactic graph convolutional networks and multihead attention layers, which are fused by the cross gates and the bilinear approach. Then, the feature pyramid networks are constructed to encode plentiful scene relationships and capture high semantics. Furthermore, to mitigate the effects of noisy annotations, we devise the multilevel losses characterized by two levels: a frame-level loss that improves noise tolerance and an instance-level loss that reduces adverse effects of negative instances. For the frame level, we adopt the Gaussian smoothing to regard noisy labels as soft labels through the partial fitting. For the instance level, we exploit a pair of structurally identical models to let them teach each other during iterations. This leads to our proposed robust video moment retrieval model, which experimentally and significantly outperforms the state-of-the-art approaches on standard public datasets ActivityCaption and textually annotated cooking scene (TACoS). We also evaluate the proposed approach on the different manual annotation noises to further demonstrate the effectiveness of our model.

IMF-MF: Interactive moment localization with adaptive multimodal fusion and self-attention

Precise video moment retrieval is crucial for enabling users to locate specific moments within a large video corpus. This paper presents Interactive Moment Localization with Multimodal Fusion (IMF-MF), a novel interactive moment localization with multimodal fusion model that leverages the power of self-attention to achieve state-of-the-art performance. IMF-MF effectively integrates query context and multimodal features, including visual and audio information, to accurately localize moments of interest. The model operates in two distinct phases: feature fusion and joint representation learning. The first phase dynamically calculates fusion weights for adapting the combination of multimodal video content, ensuring that the most relevant features are prioritized. The second phase employs bi-directional attention to tightly couple video and query features into a unified joint representation for moment localization. This joint representation captures long-range dependencies and complex patterns, enabling the model to effectively distinguish between relevant and irrelevant video segments. The effectiveness of IMF-MF is demonstrated through comprehensive evaluations on three benchmark datasets: TVR for closed-world TV episodes and Charades for open-world user-generated videos, DiDeMo dataset, Open-world, diverse video moment retrieval dataset. The empirical results indicate that the proposed approach surpasses existing state-of-the-art methods in terms of retrieval accuracy, as evaluated by metrics like Recall (R1, R5, R10, and R100) and Intersection-of-Union (IoU). The results consistently demonstrate IMF-MF’s superior performance compared to existing state-of-the-art methods, highlighting the benefits of its innovative interactive moment localization approach and the use of self-attention for feature representation and attention modeling.

Transferable Video Moment Localization by Moment-Guided Query Prompting

Video moment localization stands as a crucial task within the realm of computer vision, entailing the identification of temporal moments in untrimmed videos that bear semantic relevance to the supplied natural language queries. This work delves into a relatively unexplored facet of the task: the transferability of video moment localization models. This concern is addressed by evaluating moment localization models within a cross-domain transfer setting. In this setup, we curate multiple datasets distinguished by substantial domain gaps. The model undergoes training on one of these datasets, while validation and testing are executed using the remaining datasets. To confront the challenges inherent in this scenario, we draw inspiration from the recently introduced large-scale pre-trained vision-language models. Our focus is on exploring how the strategic utilization of these resources can bolster the capabilities of a model designed for video moment localization. Nevertheless, the distribution of language queries in video moment localization usually diverges from the text used by pre-trained models, exhibiting distinctions in aspects such as length, content, expression, and more. To mitigate the gap, this work proposes a Moment-Guided Query Prompting (MGQP) method for video moment localization. Our key idea is to generate multiple distinct and complementary prompt primitives through stratification of the original queries. Our approach is comprised of a prompt primitive constructor, a multimodal prompt refiner, and a holistic prompt incorporator. We carry out extensive experiments on Charades-STA, TACoS, DiDeMo, and YouCookII datasets, and investigate the efficacy of the proposed method using various pre-trained models, such as CLIP, ActionCLIP, CLIP4Clip, and VideoCLIP. The experimental results demonstrate the effectiveness of our proposed method.

Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language

Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each untrimmed video into multiple fixed-length video clips and then conduct multi-modal interactions with the query feature and expensive clip features for reasoning, which is infeasible for long real-world videos that span hours. Since the video is downsampled into fixed-length clips, some query-related frames may be filtered out, which will blur the specific boundary of the target moment, take the adjacent irrelevant frames as new boundaries, easily leading to cross-modal misalignment and introducing both boundary-bias and reasoning-bias. To this end, in this paper, we propose an efficient approach, SpotVMR, to trim the query-relevant clip. Besides, our proposed SpotVMR can serve as plug-and-play module, which achieves efficiency for state-of-the-art VMR methods while maintaining good retrieval performance. Especially, we first design a novel clip search model that learns to identify promising video regions to search conditioned on the language query. Then, we introduce a set of low-cost semantic indexing features to capture the context of objects and interactions that suggest where to search the query-relevant moment. Also, the distillation loss is utilized to address the optimization issues arising from end-to-end joint training of the clip selector and VMR model. Extensive experiments on three challenging datasets demonstrate its effectiveness.

TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection

Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods have been devoted to building DETR-based networks to solve both MR and HD jointly. These methods simply add two separate task heads after multi-modal feature extraction and feature interaction, achieving good performance. Nevertheless, these approaches underutilize the reciprocal relationship between two tasks. In this paper, we propose a task-reciprocal transformer based on DETR (TR-DETR) that focuses on exploring the inherent reciprocity between MR and HD. Specifically, a local-global multi-modal alignment module is first built to align features from diverse modalities into a shared latent space. Subsequently, a visual feature refinement is designed to eliminate query-irrelevant information from visual features for modal interaction. Finally, a task cooperation module is constructed to refine the retrieval pipeline and the highlight score prediction process by utilizing the reciprocity between MR and HD. Comprehensive experiments on QVHighlights, Charades-STA and TVSum datasets demonstrate that TR-DETR outperforms existing state-of-the-art methods. Codes are available at https://github.com/mingyao1120/TR-DETR.

Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding

This paper for the first time leverages multi-modal videos for weakly-supervised temporal video grounding. As labeling the video moment is labor-intensive and subjective, the weakly-supervised approaches have gained increasing attention in recent years. However, these approaches could inherently compromise performance due to inadequate supervision. Therefore, to tackle this challenge, we for the first time pay attention to exploiting complementary information extracted from multi-modal videos (e.g., RGB frames, optical flows), where richer supervision is naturally introduced in the weaklysupervised context. Our motivation is that by integrating different modalities of the videos, the model is learned from synergic supervision and thereby can attain superior generalization capability. However, addressing multiple modalities† would also inevitably introduce additional computational overhead, and might become inapplicable if a particular modality is inaccessible. To solve this issue, we adopt a novel route: building a multi-modal distillation algorithm to capitalize on the multi-modal knowledge as supervision for model training, while still being able to work with only the single modal input during inference. As such, we can utilize the benefits brought by the supplementary nature of multiple modalities, without compromising the applicability in practical scenarios. Specifically, we first propose a cross-modal mutual learning framework and train a sophisticated teacher model to learn collaboratively from the multi-modal videos. Then we identify two sorts of knowledge from the teacher model, i.e., temporal boundaries and semantic activation map. And we devise a local-global distillation algorithm to transfer this knowledge to a student model of single-modal input at both local and global levels. Extensive experiments on large-scale datasets demonstrate that our method achieves state-of-the-art performance with/without multi-modal inputs.

Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval

Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, i.e., the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In this paper, we introduce Modal-Enhanced Semantic Modeling (MESM), a novel framework for more balanced alignment through enhancing features at two levels. First, we enhance the video modality at the frame-word level through word reconstruction. This strategy emphasizes the portions associated with query words in frame-level features while suppressing irrelevant parts. Therefore, the enhanced video contains less redundant semantics and is more balanced with the textual modality. Second, we enhance the textual modality at the segment-sentence level by learning complementary knowledge from context sentences and ground-truth segments. With the knowledge added to the query, the textual modality thus maintains more meaningful semantics and is more balanced with the video modality. By implementing two levels of MESM, the semantic information from both modalities is more balanced to align, thereby bridging the modality gap. Experiments on three widely used benchmarks, including the out-of-distribution settings, show that the proposed framework achieves a new start-of-the-art performance with notable generalization ability (e.g., 4.42% and 7.69% average gains of R1@0.7 on Charades-STA and Charades-CG). The code will be available at https://github.com/lntzm/MESM.

FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild

Automatically understanding funny moments (i.e., the moments that make people laugh) when watching comedy is challenging, as they relate to various features, such as body language, dialogues and culture. In this paper, we propose FunnyNet-W, a model that relies on cross- and self-attention for visual, audio and text data to predict funny moments in videos. Unlike most methods that rely on ground truth data in the form of subtitles, in this work we exploit modalities that come naturally with videos: (a) video frames as they contain visual information indispensable for scene understanding, (b) audio as it contains higher-level cues associated with funny moments, such as intonation, pitch and pauses and (c) text automatically extracted with a speech-to-text model as it can provide rich information when processed by a Large Language Model. To acquire labels for training, we propose an unsupervised approach that spots and labels funny audio moments. We provide experiments on five datasets: the sitcoms TBBT, MHD, MUStARD, Friends, and the TED talk UR-Funny. Extensive experiments and analysis show that FunnyNet-W successfully exploits visual, auditory and textual cues to identify funny moments, while our findings reveal FunnyNet-W’s ability to predict funny moments in the wild. FunnyNet-W sets the new state of the art for funny moment detection with multimodal cues on all datasets with and without using ground truth information.

Video Moment Retrieval via Comprehensive Relation-Aware Network

Video moment retrieval aims to retrieve a target moment from an untrimmed video that semantically corresponds to the given language query. Existing methods commonly treat it as a regression task or a ranking task from the perspective of computer vision. Most of these works neglect comprehensive relations between video content and language context at a multi-granularity level and fail to efficiently model temporal relations among different video moments. In this paper, we formulate video moment retrieval into video reading comprehension by treating the input video as a text passage and language query as a question. To tackle the above impediments, we propose a Comprehensive Relation-aware Network (CRNet) to perceive comprehensive relations from extensive aspects. Specifically, we unite visual and textual features simultaneously at both clip-level and moment-level to thoroughly exploit inter-modality information, leading to a coarse-and-fine cross-modal interaction. Moreover, a background suppression module is introduced to restrain irrelevant background clips, meanwhile, a novel IoU attention mechanism and graph attention layer are efficiently devised to focus on the dependencies among highly-correlated video moments for the best choice selection. In-depth experiments on three public datasets TACoS, ActivityNet Captions, and Charades-STA demonstrate the superiority of our solution.

Temporal Sentence Grounding in Videos: A Survey and Future Directions.

Temporal sentence grounding in videos (TSGV), a.k.a. natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial style: from feature extraction from raw video and language query, to answer prediction of the target moment. Then we review the techniques for multimodal understanding and interaction, which is the key focus of TSGV for effective alignment between the two modalities. We construct a taxonomy of TSGV techniques and elaborate the methods in different categories with their strengths and weaknesses. Lastly, we discuss issues with the current TSGV research and share our insights about promising research directions.

A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach

Temporal Sentence Grounding in Videos (TSGV) , which aims to ground a natural language sentence that indicates complex human activities in an untrimmed video, has drawn widespread attention over the past few years. However, recent studies have found that current benchmark datasets may have obvious moment annotation biases, enabling several simple baselines even without training to achieve state-of-the-art (SOTA) performance. In this paper, we take a closer look at existing evaluation protocols for TSGV, and find that both the prevailing dataset splits and evaluation metrics are the devils that lead to untrustworthy benchmarking. Therefore, we propose to re-organize the two widely-used datasets, making the ground-truth moment distributions different in the training and test splits, i.e., out-of-distribution (OOD) test. Meanwhile, we introduce a new evaluation metric “dR@ n ,IoU= m ” that discounts the basic recall scores especially with small IoU thresholds, so as to alleviate the inflating evaluation caused by biased datasets with a large proportion of long ground-truth moments. New benchmarking results indicate that our proposed evaluation protocols can better monitor the research progress in TSGV. Furthermore, we propose a novel causality-based Multi-branch Deconfounding Debiasing (MDD) framework for unbiased moment prediction. Specifically, we design a multi-branch deconfounder to eliminate the effects caused by multiple confounders with causal intervention. In order to help the model better align the semantics between sentence queries and video moments, we enhance the representations during feature encoding. Specifically, for textual information, the query is parsed into several verb-centered phrases to obtain a more fine-grained textual feature. For visual information, the positional information has been decomposed from the moment features to enhance the representations of moments with diverse locations. Extensive experiments demonstrate that our proposed approach can achieve competitive results among existing SOTA approaches and outperform the base model with great gains.

Weakly-supervised content-based video moment retrieval using low-rank video representation

Content-based video moment retrieval (CVMR) aims to localize a successive sequence of frames in an untrimmed reference video, called target moment, that is semantically corresponding to a given query video. Current state-of-the-art CVMR methods are mainly developed using frame-level annotation, which is often quite expensive to collect. In this paper, we aim to develop a weakly-supervised CVMR method, which uses coarse-grained video-level annotations during training. Under weak supervision, video localizers require more discriminative frame-level video features. To achieve this goal, we proposed a novel prior, termed low-rank prior, based on an observation that the frame-level feature of a video should have low-rank properties. We demonstrated that the low-rank features are more discriminative and are beneficial to accurately localize the action boundaries. To produce a low-rank feature, we designed a low-rank feature reconstruction (LFR) operator. A new differentiable matrix decomposition approach is proposed to generate the low-rank reconstruction of the input matrix, meanwhile ensuring that the matrix decomposition process is differentiable. Based on the LFR, we developed a new weakly-supervised CVMR model which produces low-rank video representation and performs semantic consistency measures to discover the semantically matched segment in the reference video to the query video. Extensive experiments demonstrate that our method outperforms state-of-the-art weakly-supervised methods consistently and even achieves competing performance to fully-supervised baselines.

Cross-Modal Interaction Network for Video Moment Retrieval

The video moment retrieval task aims to fetch a target moment in an untrimmed video, which best matches the semantics of a sentence query. Existing methods mainly focus on utilizing two separate modules: one learns intra-modal relations to understand video and query contents, and the other explores inter-modal interactions to build a semantic bridge between video and language. However, intra-modal relations information can be easily overlooked when capturing inter-modal interactions. In fact, intra-modal relations and inter-modal interactions can be learned simultaneously within a unified module to make video and sentence guide each other. Towards this end, we propose a Cross-Modal Interaction Network (CMIN) for video moment retrieval by jointly exploring the intra-modal relations and inter-modal interactions between video frames and query words. In CMIN, a query-guided channel attention module is designed to suppress query-irrelevant visual features and enhance crucial contents; then a cross-attention module simultaneously considers intra-modal relations within each modality and fine-grained inter-modal interactions between frames and words, to enhance the semantic relevance between video and sentence query. Compared to the state-of-the-art methods, the experiments on two public datasets (Charades-STA and TACoS) demonstrate the superiority of our method.

Progressive Localization Networks for Language-Based Moment Localization

This article targets the task of language-based video moment localization. The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, then match them with the given query to determine the target moment. However, candidate moments generated with a fixed temporal granularity may be suboptimal to handle the large variation in moment lengths. To this end, we propose a novel multi-stage Progressive Localization Network (PLN) that progressively localizes the target moment in a coarse-to-fine manner. Specifically, each stage of PLN has a localization branch and focuses on candidate moments that are generated with a specific temporal granularity. The temporal granularities of candidate moments are different across the stages. Moreover, we devise a conditional feature manipulation module and an upsampling connection to bridge the multiple localization branches. In this fashion, the later stages are able to absorb the previously learned information, thus facilitating the more fine-grained localization. Extensive experiments on three public datasets demonstrate the effectiveness of our proposed PLN for language-based moment localization, especially for localizing short moments in long videos.

A Survey on Video Moment Localization

Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.