Shuang Li

Xinyu Lin, Jinxing Li, Zeyu Ma et al. · mit

Thanks for the cross-modal retrieval techniques, visible-infrared (RGB-IR) person re-identification (Re-ID) is achieved by projecting them into a common space, allowing person Re-ID in 24-hour surveillance systems. However, with respect to the probe-to-gallery, almost all existing RGB-IR based cross-modal person Re-ID methods focus on image-to-image matching, while the video-to-video matching which contains much richer spatial- and temporal-information remains under-explored. In this paper, we primarily study the video-based cross-modal person Re-ID method. To achieve this task, a video-based RGB-IR dataset is constructed, in which 927 valid identities with 463,259 frames and 21,863 tracklets captured by 12 RGB/IR cameras are collected. Based on our constructed dataset, we prove that with the increase of frames in a tracklet, the performance does meet more enhancement, demonstrating the significance of video-to-video matching in RGB-IR person Re-ID. Additionally, a novel method is further proposed, which not only projects two modalities to a modal-invariant subspace, but also extracts the temporal-memory for motion-invariant. Thanks to these two strategies, much better results are achieved on our video-based cross-modal person Re-ID. The code and dataset are released at: https://github.com/VCMproject233/MITML.

Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu et al. · deepmind, mit

Building 3D maps of the environment is central to robot navigation, planning, and interaction with objects in a scene. Most existing approaches that integrate semantic concepts with 3D maps largely remain confined to the closed-set setting: they can only reason about a finite set of concepts, pre-defined at training time. Further, these maps can only be queried using class labels, or in recent work, using text prompts. We address both these issues with ConceptFusion, a scene representation that is (1) fundamentally open-set, enabling reasoning beyond a closed set of concepts and (ii) inherently multimodal, enabling a diverse range of possible queries to the 3D map, from language, to images, to audio, to 3D geometry, all working in concert. ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio. We demonstrate that pixel-aligned open-set features can be fused into 3D maps via traditional SLAM and multi-view fusion approaches. This enables effective zero-shot spatial reasoning, not needing any additional training or finetuning, and retains long-tailed concepts better than supervised approaches, outperforming them by more than 40% margin on 3D IoU. We extensively evaluate ConceptFusion on a number of real-world datasets, simulated home environments, a real-world tabletop manipulation task, and an autonomous driving platform. We showcase new avenues for blending foundation models with 3D open-set multimodal mapping. For more information, visit our project page https://concept-fusion.github.io or watch our 5-minute explainer video https://www.youtube.com/watch?v=rkXgws8fiDs

Shuang Li, Jiaxu Leng, Changjiang Kuang et al.

Video-based Visible-Infrared Person Re-Identification (VVI-ReID) aims to match pedestrian sequences across modalities by extracting modality-invariant sequence-level features. As a high-level semantic representation, language provides a consistent description of pedestrian characteristics in both infrared and visible modalities. Leveraging the Contrastive Language-Image Pre-training (CLIP) model to generate video-level language prompts and guide the learning of modality-invariant sequence-level features is theoretically feasible. However, the challenge of generating and utilizing modality-shared video-level language prompts to address modality gaps remains a critical problem. To address this problem, we propose a simple yet powerful framework, video-level language-driven VVI-ReID (VLD), which consists of two core modules: invariant-modality language prompting (IMLP) and spatial-temporal prompting (STP). IMLP employs a joint fine-tuning strategy for the visual encoder and the prompt learner to effectively generate modality-shared text prompts and align them with visual features from different modalities in CLIP's multimodal space, thereby mitigating modality differences. Additionally, STP models spatiotemporal information through two submodules, the spatial-temporal hub (STH) and spatial-temporal aggregation (STA), which further enhance IMLP by incorporating spatiotemporal information into text prompts. The STH aggregates and diffuses spatiotemporal information into the [CLS] token of each frame across the vision transformer (ViT) layers, whereas STA introduces dedicated identity-level loss and specialized multihead attention to ensure that the STH focuses on identity-relevant spatiotemporal feature aggregation. The VLD framework achieves state-of-the-art results on two VVI-ReID benchmarks. The code will be released at https://github.com/Visuang/VLD.

Yujie Yang, Shuang Li, Jun Ye et al.

Video-based Visible-Infrared person re-identification (VVI-ReID) aims to retrieve the same pedestrian across visible and infrared modalities from video sequences. Existing methods tend to exploit modality-invariant visual features but largely overlook gait features, which are not only modality-invariant but also rich in temporal dynamics, thus limiting their ability to model the spatiotemporal consistency essential for cross-modal video matching. To address these challenges, we propose a DINOv2-Driven Gait Representation Learning (DinoGRL) framework that leverages the rich visual priors of DINOv2 to learn gait features complementary to appearance cues, facilitating robust sequence-level representations for cross-modal retrieval. Specifically, we introduce a Semantic-Aware Silhouette and Gait Learning (SASGL) model, which generates and enhances silhouette representations with general-purpose semantic priors from DINOv2 and jointly optimizes them with the ReID objective to achieve semantically enriched and task-adaptive gait feature learning. Furthermore, we develop a Progressive Bidirectional Multi-Granularity Enhancement (PBMGE) module, which progressively refines feature representations by enabling bidirectional interactions between gait and appearance streams across multiple spatial granularities, fully leveraging their complementarity to enhance global representations with rich local details and produce highly discriminative features. Extensive experiments on HITSZ-VCM and BUPT datasets demonstrate the superiority of our approach, significantly outperforming existing state-of-the-art methods.

Shuanglin Yan, Neng Dong, Shuang Li et al.

Visible-Infrared Person Re-identification (VIReID) aims to match visible and infrared pedestrian images, but the modality differences and the complexity of identity features make it challenging. Existing methods rely solely on identity label supervision, which makes it difficult to fully extract high-level semantic information. Recently, vision-language pre-trained models have been introduced to VIReID, enhancing semantic information modeling by generating textual descriptions. However, such methods do not explicitly model body shape features, which are crucial for cross-modal matching. To address this, we propose an effective Body Shape-aware Textual Alignment (BSaTa) framework that explicitly models and utilizes body shape information to improve VIReID performance. Specifically, we design a Body Shape Textual Alignment (BSTA) module that extracts body shape information using a human parsing model and converts it into structured text representations via CLIP. We also design a Text-Visual Consistency Regularizer (TVCR) to ensure alignment between body shape textual representations and visual body shape features. Furthermore, we introduce a Shape-aware Representation Learning (SRL) mechanism that combines Multi-text Supervision and Distribution Consistency Constraints to guide the visual encoder to learn modality-invariant and discriminative identity features, thus enhancing modality invariance. Experimental results demonstrate that our method achieves superior performance on the SYSU-MM01 and RegDB datasets, validating its effectiveness.

Yunzhu Li, Shuang Li, Vincent Sitzmann et al.

Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far beyond the reach of current robots. In this work, we desire to learn models for dynamic 3D scenes purely from 2D visual observations. Our model combines Neural Radiance Fields (NeRF) and time contrastive learning with an autoencoding framework, which learns viewpoint-invariant 3D-aware scene representations. We show that a dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks involving both rigid bodies and fluids, where the target is specified in a viewpoint different from what the robot operates on. When coupled with an auto-decoding framework, it can even support goal specification from camera viewpoints that are outside the training distribution. We further demonstrate the richness of the learned 3D dynamics model by performing future prediction and novel view synthesis. Finally, we provide detailed ablation studies regarding different system designs and qualitative analysis of the learned representations.

Peng Gao, Pan Lu, Hongsheng Li et al.

In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA). Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features.To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage. The question-guided convolution can tightly couple the textual and visual information but also introduce more parameters when learning kernels. We apply the group convolution, which consists of question-independent kernels and question-dependent kernels, to reduce the parameter size and alleviate over-fitting. The hybrid convolution can generate discriminative multi-modal features with fewer parameters. The proposed approach is also complementary to existing bilinear pooling fusion and attention based VQA methods. By integrating with them, our method could further boost the performance. Extensive experiments on public VQA datasets validate the effectiveness of QGHC.

Shuang Li, Slawomir Bak, Peter Carr et al.

Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all frames. In practice, people are often partially occluded, which can corrupt the extracted features. Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts. This allows useful information to be extracted from all frames without succumbing to occlusions and misalignments. The network learns multiple spatial attention models and employs a diversity regularization term to ensure multiple models do not discover the same body part. Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention. As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence. Extensive evaluations on three datasets show that our framework outperforms the state-of-the-art approaches by large margins on multiple metrics.

Tong Xiao, Shuang Li, Bochao Wang et al.

Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are unavailable and the target person needs to be searched from a gallery of whole scene images. To close the gap, we propose a new deep learning framework for person search. Instead of breaking it down into two separate tasks---pedestrian detection and person re-identification, we jointly handle both aspects in a single convolutional neural network. An Online Instance Matching (OIM) loss function is proposed to train the network effectively, which is scalable to datasets with numerous identities. To validate our approach, we collect and annotate a large-scale benchmark dataset for person search. It contains 18,184 images, 8,432 identities, and 96,143 pedestrian bounding boxes. Experiments show that our framework outperforms other separate approaches, and the proposed OIM loss function converges much faster and better than the conventional Softmax loss.