People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique challenges to recognizing social relationships, requiring understanding and capturing the essence of these contexts from visual appearances. However, current methods of social relationship understanding rely on the basic classification paradigm of detected persons and objects, which fails to understand the comprehensive context and often overlooks decisive social factors, especially subtle visual cues. To highlight the social-aware context and intricate details, we propose a novel approach that recognizes contextual social relationships (ConSoRs) from a social cognitive perspective. Specifically, to incorporate social-aware semantics, we build a lightweight adapter upon the frozen contrastive language-image pretraining (CLIP) to learn social concepts via our novel multimodal side adapter tuning mechanism. Furthermore, we construct social-aware descriptive language prompts (e.g., scene, activity, objects, and emotions) with social relationships for each image, and then compel ConSoR to concentrate more intensively on the decisive visual social factors via visual-linguistic contrasting. Impressively, ConSoR outperforms previous methods with a 7.6% gain on the people-in-social-context (PISC) dataset and a 9.8% increase on the people-in-photo-album (PIPA) benchmark. Furthermore, we observe that ConSoR excels at finding critical visual evidence to reveal social relationships. Code is available at https://github.com/starsholic/ConSoR.

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data pipeline for YouTube videos and their closed captions (CC), resulting in Live-CC-10M pre-training set and Live-WhisperX-408K high-quality supervised fine-tuning (SFT) set. Remarkably, even without SFT, the pre-trained model LiveCC-7B demonstrates significant improvements in general video QA and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new benchmark LiveSports-3K, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final model LiveCC-7B can surpass LLaVA-Video-72B in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B scale on popular benchmarks such as VideoMME, demonstrating its broad generalizability. All resources of this paper have been released at showlab.github.io/livecc.

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions—including a novel “expert commentary” done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. https://ego-exo4d-data.org/

Recent Large Language Models (LLMs) have been en-hanced with vision capabilities, enabling them to compre-hend images, videos, and interleaved vision-language con-tent. However, the learning methods of these large multi-modal models (LMMs) typically treat videos as predeter-mined clips, rendering them less effective and efficient at handling streaming video inputs. In this paper, we pro-pose a novel Learning-In- Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time dialogue within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training ob-jective designed to perform language modeling for contin-uous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming di-alogue format, and (3) an optimized inference pipeline to speed up interactive chat in real-world video streams. With our LIVE framework, we develop a simplified model called VideoLLM-online and demonstrate its significant advan-tages in processing streaming videos. For instance, our VideoLLM-online-7B model can operate at over 10 FPS on an A100 GPU for a 5-minute video clip from Ego4D narration. Moreover, VideoLLM-online also showcases state-of-the-art performance on public offline video bench-marks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at showlab.github. iolvideollm-online.

The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs, greatly reducing computational costs while still achieving promising performance. However, training SparseFormers from scratch is still expensive, and scaling up the number of parameters can be challenging. In this paper, we propose to bootstrap SparseFormers from ViT-based vision foundation models in a simple and efficient way. Since the majority of SparseFormer blocks are the standard transformer ones, we can inherit weights from large-scale pre-trained vision transformers and freeze them as much as possible. Therefore, we only need to train the SparseFormer-specific lightweight focusing transformer to adjust token RoIs and fine-tune a few early pre-trained blocks to align the final token representation. In such a way, we can bootstrap SparseFormer architectures from various large-scale pre-trained models (e.g., IN-21 K pre-trained AugRegs or CLIPs) using a rather smaller amount of training samples (e.g., IN-IK) and without labels or captions within just a few hours. As a result, the bootstrapped unimodal SparseFormer (from AugReg-ViT-L/16-384) can reach 84.9% accuracy on IN-IK with only 49 tokens, and the multimodal SparseFormer from CLIPs also demonstrates notable zero-shot performance with highly reduced computational cost without seeing any caption during the bootstrapping procedure. In addition, CLIP-bootstrapped SparseFormers, which align the output space with language without seeing a word, can serve as efficient vision encoders in multimodal large language models. Code and models are available at https://github.com/showlab/sparseformer

We present Ego-Exo4D, a diverse, large-scale multi-modal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured ego-centric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is un-precedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions-including a novel “expert commentary” done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community.

We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA addresses these challenges by integrating a Sparse Dense Sampling strategy into the video-LLM, which balances temporal context and spatial detail within computational constraints. Additionally, we propose a One-Token-Seg-All approach using a specially designed <TRK> token, enabling the model to segment and track objects across multiple frames. Extensive evaluations on diverse benchmarks, including our newly introduced ReasonVOS benchmark, demonstrate VideoLISA's superior performance in video object segmentation tasks involving complex reasoning, temporal understanding, and object tracking. While optimized for videos, VideoLISA also shows promising generalization to image segmentation, revealing its potential as a unified foundation model for language-instructed object segmentation. Code and model will be available at: https://github.com/showlab/VideoLISA.

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Although learnable approaches like Q-Former and Perceiver Resampler have been developed to reduce the vision token burden, they overlook the context causally modeled by LLMs (i.e., key-value cache), potentially leading to missed visual cues when addressing user queries. In this paper, we introduce a novel approach to reduce vision compute by leveraging redundant vision tokens ``skipping layers'' rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video. Specifically, for certain transformer layer, we learn to skip the computation for a high proportion (e.g., 80\%) of vision tokens, passing them directly to the next layer. This approach significantly enhances model efficiency, achieving approximately 42% time and 30% memory savings for the entire training. Moreover, our method reduces the computation in the context and avoid decreasing the vision tokens, thus preserving or even improving performance compared to the vanilla model. We conduct extensive experiments to demonstrate the effectiveness of VideoLLM-MoD, showing its state-of-the-art results on multiple benchmarks, including narration, forecasting, and summarization tasks in COIN, Ego4D, and Ego-Exo4D datasets. The code and checkpoints will be made available at github.com/showlab/VideoLLM-online.

Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances) from demonstration videos and apply them to a target image like a user's AR glass view. This video-to-image affordance grounding task is challenging due to (1) the need to predict fine-grained affordances, and (2) the limited training data, which inadequately covers video-image discrepancies and negatively impacts grounding. To tackle them, we propose Affordance Transformer (Afformer), which has a fine-grained transformer-based decoder that gradually refines affordance grounding. Moreover, we introduce Mask Affordance Hand (MaskAHand), a self-supervised pre-training technique for synthesizing video-image data and simulating context changes, enhancing affordance grounding across video-image discrepancies. Afformer with MaskAHand pre-training achieves state-of-the-art performance on multiple benchmarks, including a sub-stantial 37% improvement on the OPRA dataset. Code is made available at https://github.com/showlab/afformer.

The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies.Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task.In this paper, we build a novel task-oriented VQA dataset, called GazeVQA, for collaborative tasks where gaze information is captured during the task process.GazeVQA is designed with a novel QA format that covers thirteen different reasoning types to capture multiple aspects of task information and user intent.For each participant, GazeVQA consists of more than 1,100 textual questions and more than 500 labeled images that were annotated with the assistance of the Segment Anything Model.In total, 2,967 video clips, 12,491 labeled images, and 25,040 questions from 22 participants were included in the dataset.Additionally, inspired by the assisting models and common ground theory for industrial task collaboration, we propose a new AI model called AssistGaze that is designed to answer the questions with three different answer types, namely textual, image, and video.AssistGaze can effectively ground the perceptual input into semantic information while reducing ambiguities.We conduct comprehensive experiments to demonstrate the challenges of GazeVQA 1 and the effectiveness of AssistGaze 2 .

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most methods in this direction develop task-specific models that are trained with type-specific labels, such as moment retrieval (time interval) and highlight detection (worthiness curve), which limits their abilities to generalize to various VTG tasks and labels. In this paper, we propose to Unify the diverse VTG labels and tasks, dubbed UniVTG, along three directions: Firstly, we revisit a wide range of VTG labels and tasks and define a unified formulation. Based on this, we develop data annotation schemes to create scalable pseudo supervision. Secondly, we develop an effective and flexible grounding model capable of addressing each task and making full use of each label. Lastly, thanks to the unified framework, we are able to unlock temporal grounding pretraining from large-scale diverse labels and develop stronger grounding abilities e.g., zero-shot grounding. Extensive experiments on three tasks (moment retrieval, highlight detection and video summarization) across seven datasets (QVHighlights, Charades-STA, TACoS, Ego4D, YouTube Highlights, TVSum, and QFVS) demonstrate the effectiveness and flexibility of our proposed framework. The codes are available at https://github.com/showlab/UniVTG.

With the development of the parameterized hand model (e.g. MANO), it is possible to reconstruct the 3D hand mesh from a single 2D hand image by learning a few hand model parameters, rather than estimating hundreds of vertices on the mesh. However, it is highly non-linear to learn these parameters from the 2D hand image, as there is no explicit spatial correspondence between these parameters and image pixels. In this paper, we successfully leverage the graph convolutional network (GCN) to capture implicit spatial cues for fitting the well-known MANO hand model, thus greatly improving the performance of monocular 3D hand reconstruction. Our proposed MANO-GCN establishes the spatial hand mesh and hand joints graph for learning MANO parameters, with node features propagated along edges to utilize the spatial information. Among all monocular 3D hand reconstruction methods with MANO hand model, MANO-GCN achieves state-of-the-art accuracy on public FreiHAND and HO-3D benchmarks, without any bells and whistles. Code is available at https://github.com/ChenJoya/manogcn.

Recent years have witnessed the booming of online video platforms. Along this line, a graph to illustrate social relation among characters has been long expected to not only benefit the audiences for better understanding the story, but also support the fine-grained video analysis task in a semantic way. Unfortunately, though we humans could easily infer the social relations among characters, it is still an extremely challenging task for intelligent systems to automatically capture the social relation by absorbing multi-modal cues. Besides, they fail to describe the relations among multiple characters in a graph-generation perspective. To that end, inspired by the human inference ability on social relationship, we propose a novel Hierarchical- Cumulative Graph Convolutional Network (HC-GCN) to generate the social relation graph for multiple characters in the video. Specifically, we first integrate the short-term multi-modal cues, including visual, textual and audio information, to generate the frame-level graphs for part of characters via multimodal graph convolution technique. While dealing with the video-level aggregation task, we design an end-to-end framework to aggregate all frame-level subgraphs along the temporal trajectory, which results in a global video-level social graph with various social relationships among multiple characters. Extensive validations on two real-world large-scale datasets demonstrate the effectiveness of our proposed method compared with SOTA baselines.

To train accurate deep object detectors under the extreme foreground-background imbalance, heuristic sampling methods are always necessary, which either re-sample a subset of all training samples (hard sampling methods, e.g. biased sampling, OHEM), or use all training samples but re-weight them discriminatively (soft sampling methods, e.g. Focal Loss, GHM). In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors. While previous studies have shown that training detectors without heuristic sampling methods would significantly degrade accuracy, we reveal that this degradation comes from an unreasonable classification gradient magnitude caused by the imbalance, rather than a lack of re-sampling/re-weighting. Motivated by our discovery, we propose a simple yet effective Sampling-Free mechanism to achieve a reasonable classification gradient magnitude by initialization and loss scaling. Unlike heuristic sampling methods with multiple hyperparameters, our Sampling-Free mechanism is fully data diagnostic, without laborious hyperparameters searching. We verify the effectiveness of our method in training anchor-based and anchor-free object detectors, where our method always achieves higher detection accuracy than heuristic sampling methods on COCO and PASCAL VOC datasets. Our Sampling-Free mechanism provides a new perspective to address the foreground-background imbalance. Our code is released at https://github.com/ChenJoya/sampling-free.

The top accuracy of object detection to date is led by region-based approaches, where the per-region stage is responsible for recognizing proposals generated by the region proposal network. In that stage, sampling heuristics (e.g., OHEM, IoU-balanced sampling) is always applied to select a part of examples during training. But nowadays, existing samplers ignore the overlaps among examples, which may result in some low-quality predictions preserved. To mitigate the issue, we propose Overlap Sampler that selects examples according to the overlaps among examples, which enables the training to focus on the important examples. Benefitted from it, the Faster R-CNN could obtain impressively 1.5 points higher Average Precision (AP) on the challenging COCO benchmark, a state-of-the-art result among existing samplers for region-based detectors. Moreover, the proposed sampler also yields considerable improvements for the instance segmentation task. Our code is released at https://github.com/ChenJoya/overlap-sampler.