Visual Ground Research Articles

Parallel Vertex Diffusion for Unified Visual Grounding

Unified visual grounding (UVG) capitalizes on a wealth of task-related knowledge across various grounding tasks via one-shot training, which curtails retraining costs and task-specific architecture design efforts. Vertex generation-based UVG methods achieve this versatility by unified modeling object box and contour prediction and provide a text-powered interface to vast related multi-modal tasks, e.g., visual question answering and captioning. However, these methods typically generate vertexes sequentially through autoregression, which is prone to be trapped in error accumulation and heavy computation, especially for high-dimension sequence generation in complex scenarios. In this paper, we develop Parallel Vertex Diffusion (PVD) based on the parallelizability of diffusion models to accurately and efficiently generate vertexes in a parallel and scalable manner. Since the coordinates fluctuate greatly, it typically encounters slow convergence when training diffusion models without geometry constraints. Therefore, we consummate our PVD by two critical components, i.e., center anchor mechanism and angle summation loss, which serve to normalize coordinates and adopt a differentiable geometry descriptor from the point-in-polygon problem of computational geometry to constrain the overall difference of prediction and label vertexes. These innovative designs empower our PVD to demonstrate its superiority with state-of-the-art performance across various grounding tasks.

Unifying Visual and Vision-Language Tracking via Contrastive Learning

Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap between different modalities, most existing trackers are designed for single or partial of these reference settings and overspecialize on the specific modality. Differently, we present a unified tracker called UVLTrack, which can simultaneously handle all three reference settings (BBOX, NL, NL+BBOX) with the same parameters. The proposed UVLTrack enjoys several merits. First, we design a modality-unified feature extractor for joint visual and language feature learning and propose a multi-modal contrastive loss to align the visual and language features into a unified semantic space. Second, a modality-adaptive box head is proposed, which makes full use of the target reference to mine ever-changing scenario features dynamically from video contexts and distinguish the target in a contrastive way, enabling robust performance in different reference settings. Extensive experimental results demonstrate that UVLTrack achieves promising performance on seven visual tracking datasets, three vision-language tracking datasets, and three visual grounding datasets. Codes and models will be open-sourced at https://github.com/OpenSpaceAI/UVLTrack.

ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding

Aiming to link natural language descriptions to specific regions in a 3D scene represented as 3D point clouds, 3D visual grounding is a very fundamental task for human-robot interaction. The recognition errors can significantly impact the overall accuracy and then degrade the operation of AI systems. Despite their effectiveness, existing methods suffer from the difficulty of low recognition accuracy in cases of multiple adjacent objects with similar appearance. To address this issue, this work intuitively introduces the human-robot interaction as a cue to facilitate the development of 3D visual grounding. Specifically, a new task termed Embodied Reference Understanding (ERU) is first designed for this concern. Then a new dataset called ScanERU is constructed to evaluate the effectiveness of this idea. Different from existing datasets, our ScanERU dataset is the first to cover semi-synthetic scene integration with textual, real-world visual, and synthetic gestural information. Additionally, this paper formulates a heuristic framework based on attention mechanisms and human body movements to enlighten the research of ERU. Experimental results demonstrate the superiority of the proposed method, especially in the recognition of multiple identical objects. Our codes and dataset are available in the ScanERU repository.

Mono3DVG: 3D Visual Grounding in Monocular Images

We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be released.

Comprehensive Visual Grounding for Video Description

The grounding accuracy of existing video captioners is still behind the expectation. The majority of existing methods perform grounded video captioning on sparse entity annotations, whereas the captioning accuracy often suffers from degenerated object appearances on the annotated area such as motion blur and video defocus. Moreover, these methods seldom consider the complex interactions among entities. In this paper, we propose a comprehensive visual grounding network to improve video captioning, by explicitly linking the entities and actions to the visual clues across the video frames. Specifically, the network consists of spatial-temporal entity grounding and action grounding. The proposed entity grounding encourages the attention mechanism to focus on informative spatial areas across video frames, albeit the entity is annotated in only one frame of a video. The action grounding dynamically associates the verbs to related subjects and the corresponding context, which keeps fine-grained spatial and temporal details for action prediction. Both entity grounding and action grounding are formulated as a unified task guided by a soft grounding supervision, which brings architecture simplification and improves training efficiency as well. We conduct extensive experiments on two challenging datasets, and demonstrate significant performance improvements of +2.3 CIDEr on ActivityNet-Entities and +2.2 CIDEr on MSR-VTT compared to state-of-the-arts.

Acute effects of negative heel shoes on perceived pain and knee biomechanical characteristics of runners with patellofemoral pain.

To determine the effects of negative heel shoes on perceived pain and knee biomechanical characteristics of runners with patellofemoral pain (PFP) during running. Sixteen runners with PFP ran in negative (-11mm drops) and positive (5mm drops) heel shoes while visual analog scale (VAS) scores, retroreflective markers, and ground reaction force were acquired by applying a 10-cm VAS, infrared motion capture system, and a three-dimensional force plate. Knee moment, patellofemoral joint stress (PFJS), and other biomechanical parameters during the stance phase were calculated based on inverse dynamics and a biomechanical model of the patellofemoral joint. The foot inclination angle, peak PFJS during the stance phase, patellofemoral joint reaction force, knee extension moment, and quadriceps force at the time of peak PFJS of runners with PFP in negative heel shoes were lower than that in positive heel shoes, no significant difference was found in VAS scores, knee flexion angle, patellofemoral contact area, and quadriceps moment arm at the time of peak PFJS. Compared to positive heel shoes, running in negative heel shoes decreases peak PFJS in runners with PFP, which may decrease patellofemoral joint loading, thus reducing the possibility of further development of PFP. Sports Science Experiment Ethics Committee of Beijing Sport University. 2023095H, April 18, 2023 (prospectively registered).

Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding.

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention operation with quadratic time complexity. To address this issue, we present a new multimodal transformer architecture, coined as Dynamic Mutilmodal detection transformer (DETR) (Dynamic MDETR), by decoupling the whole grounding process into encoding and decoding phases. The key observation is that there exists high spatial redundancy in images. Thus, we devise a new dynamic multimodal transformer decoder by exploiting this sparsity prior to speed up the visual grounding process. Specifically, our dynamic decoder is composed of a 2D adaptive sampling module and a text guided decoding module. The sampling module aims to select these informative patches by predicting the offsets with respect to a reference point, while the decoding module works for extracting the grounded object information by performing cross attention between image features and text features. These two modules are stacked alternatively to gradually bridge the modality gap and iteratively refine the reference point of grounded object, eventually realizing the objective of visual grounding. Extensive experiments on five benchmarks demonstrate that our proposed Dynamic MDETR achieves competitive trade-offs between computation and accuracy. Notably, using only 9% feature points in the decoder, we can reduce ∼44% GFLOPs of the multimodal transformer, but still get higher accuracy than the encoder-only counterpart. With the same number of encoder layers as TransVG, our Dynamic MDETR (ResNet-50) outperforms TransVG (ResNet-101) but only brings marginal extra computational cost relative to TransVG. In addition, to verify its generalization ability and scale up our Dynamic MDETR, we build the first one-stage CLIP empowered visual grounding framework, and achieve the state-of-the-art performance on these benchmarks.

Word2Pix: Word to Pixel Cross-Attention Transformer in Visual Grounding.

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual features for target localization. Such a formulation provides insufficient ability to model query at the word level, and therefore is prone to neglect words that may not be the most important ones for a sentence but are critical for the referred object. In this article, we propose Word2Pix: a one-stage visual grounding network based on the encoder-decoder transformer architecture that enables learning for textual to visual feature correspondence via word to pixel attention. Each word from the query sentence is given an equal opportunity when attending to visual pixels through multiple stacks of transformer decoder layers. In this way, the decoder can learn to model the language query and fuse language with the visual features for target prediction simultaneously. We conduct the experiments on RefCOCO, RefCOCO+, and RefCOCOg datasets, and the proposed Word2Pix outperforms the existing one-stage methods by a notable margin. The results obtained also show that Word2Pix surpasses the two-stage visual grounding models, while at the same time keeping the merits of the one-stage paradigm, namely, end-to-end training and fast inference speed. Code is available at https://github.com/azurerain7/Word2Pix.

End-to-end Visual Grounding Based on Query Text Guidance and Multi-stage Reasoning

<p>Visual grounding locates target objects or areas in the image based on natural language expression. Most current methods extract visual features and text embeddings independently, and then carry out complex fusion reasoning to locate target objects mentioned in the query text. However, such independently extracted visual features often contain many features that are irrelevant to the query text or misleading, thus affecting the subsequent multimodal fusion module, and deteriorating target localization. This study introduces a combined network model based on the transformer architecture, which realizes more accurate visual grounding by using query text to guide visual feature generation and multi-stage fusion reasoning. Specifically, the visual feature generation module reduces the interferences of irrelevant features and generates visual features related to query text through the guidance of query text features. The multi-stage fused reasoning module uses the relevant visual features obtained by the visual feature generation module and the query text embeddings for multi-stage interactive reasoning, further infers the correlation between the target image and the query text, so as to achieve the accurate localization of the object described by the query text. The effectiveness of the proposed model is experimentally verified on five public datasets and the model outperforms state-of-the-art methods. It achieves an improvement of 1.04%, 2.23%, 1.00% and +2.51% over the previous state-of-the-art methods in terms of the top-1 accuracy on TestA and TestB of the RefCOCO and RefCOCO+ datasets, respectively.</p> <p> </p>

Engineering Meter-scale Porous Media Flow Experiments for Quantitative Studies of Geological Carbon Sequestration

This technical note describes the FluidFlower concept, a new laboratory infrastructure for geological carbon storage research. The highly controlled and adjustable system produces a strikingly visual physical ground truth of studied processes for model validation, comparison and forecasting, including detailed physical studies of the behavior and storage mechanisms of carbon dioxide and its derivative forms in relevant geological settings for subsurface carbon storage. The design, instrumentation, structural aspects and methodology are described. Furthermore, we share engineering insights into construction, operation, fluid considerations and fluid resetting in the porous media. The new infrastructure enables researchers to study variability between repeated CO2 injections, making the FluidFlower concept a suitable tool for sensitivity studies on a range of determining carbon storage parameters in varying geological formations.

Language-Guided Progressive Attention for Visual Grounding in Remote Sensing Images

Language-Guided Progressive Attention for Visual Grounding in Remote Sensing Images

A Masked Reference Token Supervision based Iterative Visual-language Framework for Robust Visual Grounding

A Masked Reference Token Supervision based Iterative Visual-language Framework for Robust Visual Grounding

Language Query-Based Transformer With Multiscale Cross-Modal Alignment for Visual Grounding on Remote Sensing Images

Language Query-Based Transformer With Multiscale Cross-Modal Alignment for Visual Grounding on Remote Sensing Images

CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding

CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding

End-to-End Visual Grounding Framework for Multimodal NER in Social Media Posts

End-to-End Visual Grounding Framework for Multimodal NER in Social Media Posts

A Regionally Indicated Visual Grounding Network for Remote Sensing Images

A Regionally Indicated Visual Grounding Network for Remote Sensing Images

ViewInfer3D: 3D Visual Grounding based on Embodied Viewpoint Inference

ViewInfer3D: 3D Visual Grounding based on Embodied Viewpoint Inference

Multi-Stage Synergistic Aggregation Network for Remote Sensing Visual Grounding

Multi-Stage Synergistic Aggregation Network for Remote Sensing Visual Grounding

How direct is the link between words and images?

Abstract Günther et al. (2022) investigated the relationship between words and images in which they concluded the possibility of a direct link between words and embodied experience. In their study, participants were presented with a target noun and a pair of images, one chosen by their model and another chosen randomly. Participants were asked to select the image that best matched the target noun. Building upon their work, we addressed the following questions. 1. Apart from utilizing visually embodied simulation, what other strategies subjects might have used? How much does this setup rely on visual information? Can it be solved using textual representations? 2. Do current visually-grounded embeddings explain subjects’ selection behavior better than textual embeddings? 3. Does visual grounding improve the representations of both concrete and abstract words? For this aim, we designed novel experiments based on pre-trained word embeddings. Our experiments reveal that subjects’ selection behavior is explained to a large extend on text-based embeddings and word-based similarities. Visually grounded embeddings offered modest advantages over textual embeddings in certain cases. These findings indicate that the experiment by Günther et al. (2022) may not be well suited for tapping into the perceptual experience of participants, and the extent to which it measures visually grounded knowledge is unclear.

Language with vision: A study on grounded word and sentence embeddings

Grounding language in vision is an active field of research seeking to construct cognitively plausible word and sentence representations by incorporating perceptual knowledge from vision into text-based representations. Despite many attempts at language grounding, achieving an optimal equilibrium between textual representations of the language and our embodied experiences remains an open field. Some common concerns are the following. Is visual grounding advantageous for abstract words, or is its effectiveness restricted to concrete words? What is the optimal way of bridging the gap between text and vision? To what extent is perceptual knowledge from images advantageous for acquiring high-quality embeddings? Leveraging the current advances in machine learning and natural language processing, the present study addresses these questions by proposing a simple yet very effective computational grounding model for pre-trained word embeddings. Our model effectively balances the interplay between language and vision by aligning textual embeddings with visual information while simultaneously preserving the distributional statistics that characterize word usage in text corpora. By applying a learned alignment, we are able to indirectly ground unseen words including abstract words. A series of evaluations on a range of behavioral datasets shows that visual grounding is beneficial not only for concrete words but also for abstract words, lending support to the indirect theory of abstract concepts. Moreover, our approach offers advantages for contextualized embeddings, such as those generated by BERT (Devlin et al, 2018), but only when trained on corpora of modest, cognitively plausible sizes. Code and grounded embeddings for English are available at (https://github.com/Hazel1994/Visually_Grounded_Word_Embeddings_2).