In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without additional model training. To evaluate this task, we curate a benchmark dataset, AVED-Bench, designed explicitly for zero-shot audio-video editing. AVED-Bench includes 110 videos, each with a 10-second duration, spanning 11 categories from VGGSound. It offers diverse prompts and scenarios that require precise alignment between auditory and visual elements, enabling robust evaluation. We identify limitations in existing zero-shot audio and video editing methods, particularly in synchronization and coherence between modalities, which often result in inconsistent outcomes. To address these challenges, we propose AVED, a zero-shot cross-modal delta denoising framework that leverages audio-video interactions to achieve synchronized and coherent edits. AVED demonstrates superior results on both AVED-Bench and the recent OAVE dataset to validate its generalization capabilities. Our codes, data, and results are available at https://genjib.github.io/project_page/AVED/index.html

Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps. However, accurately localizing timestamps in videos remains challenging for Video LLMs when relying solely on temporal token prediction. Our proposed TimeRefine addresses this challenge in two ways. First, instead of directly predicting the start and end timestamps, we reformulate temporal grounding as a temporal refinement task: the model first makes rough predictions and then refines them by predicting offsets to the target segment. This refining process is repeated multiple times, through which the model progressively improves its own temporal localization accuracy. Second, to enhance the model’s temporal perception capabilities, we incorporate an auxiliary prediction head that applies a larger penalty as a predicted segment deviates further from the ground truth, encouraging more precise temporal localizations. Our plug-and-play method can be integrated into most LLM-based temporal grounding approaches. The experimental results demonstrate that TimeRefine achieves 3.6% and 5.0% mIoU improvements on the ActivityNet and Charades-STA datasets, respectively. Code and pretrained models are available at https://github.com/SJTUwxz/TimeRefine_code.

Visual Planning for Assistance (VPA) aims to predict a sequence of user actions required to achieve a specified goal based on a video showing the user’s progress. Although recent advances in multimodal large language models (MLLMs) have shown promising results in video understanding, long-horizon visual planning remains a challenging problem. We identify two challenges in training large MLLMs for video-based planning tasks: (1) scarcity of procedural annotations, limiting the model’s ability to learn procedural task dynamics effectively, and (2) inefficiency of next-token prediction objective to explicitly capture the structured action space for visual planning when compared to free-form, natural language. To tackle data scarcity, we introduce Auxiliary Task Augmentation. We design and train our model on auxiliary tasks relevant to long-horizon video-based planning (e.g., goal prediction) to augment the model’s planning ability. To more explicitly model the structured action space unique to visual planning tasks, we leverage Multi-token Prediction, extending traditional next-token prediction by using multiple heads to predict multiple future tokens during training. Our approach, VideoPlan, achieves state-of-the-art VPA performance on the COIN and CrossTask datasets, surpassing prior methods by 7.3% and 3.4%, respectively, when predicting 3 future actions. We further extend our method to the challenging Ego4D Long-term Action Anticipation task, and show that it is on par with the state-of-the-art approaches despite not using specialized egocentric features. Code is available at https://github.com/CeeZh/VideoPlan.

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are constrained by frame limitations, often losing essential temporal details needed for accurate event localization in extended video content. We propose ReVisionLLM, a recursive vision-language model designed to locate events in hour-long videos. Inspired by human search strategies, our model initially targets broad segments of interest, progressively revising its focus to pinpoint exact temporal boundaries. Our model can seamlessly handle videos of vastly different lengths—from minutes to hours. We also introduce a hierarchical training strategy that starts with short clips to capture distinct events and progressively extends to longer videos. To our knowledge, ReVision-LLM is the first VLM capable of temporal grounding in hour-long videos, outperforming previous state-of-the-art methods across multiple datasets by a significant margin (e.g., +2.6% [email protected] on MAD). The code is available at https://github.com/Tanveer81/ReVisionLLM

Video Question Answering (VQA) in long videos poses the key challenge of extracting relevant information and modeling long-range dependencies from many redundant frames. The self-attention mechanism provides a general solution for sequence modeling, but it has a prohibitive cost when applied to a massive number of spatiotemporal tokens in long videos. Most prior methods rely on compression strategies to lower the computational cost, such as reducing the input length via sparse frame sampling or compressing the output sequence passed to the large language model (LLM) via space-time pooling. However, these naive approaches over-represent redundant information and often miss salient events or fast-occurring space-time patterns. In this work, we introduce BIMBA, an efficient state-space model to handle long-form videos. Our model leverages the selective scan algorithm to learn to effectively select critical information from high-dimensional video and transform it into a reduced token sequence for efficient LLM processing. Extensive experiments demonstrate that BIMBA achieves state-of-the-art accuracy on multiple long-form VQA benchmarks, including PerceptionTest, NExT-QA, EgoSchema, VNBench, LongVideoBench, Video-MME, and MLVU. Code and models are available at https://sites.google.com/view/bimba-mllm.

We present Basket, a large-scale basketball video dataset for fine-grained skill estimation. Basket contains 4,477 hours of video capturing 32,232 basketball players from all over the world. Compared to prior skill estimation datasets, our dataset includes a massive number of skilled participants with unprecedented diversity in terms of gender, age, skill level, geographical location, etc. Basket includes 20 fine-grained basketball skills, challenging modern video recognition models to capture the intricate nuances of player skill through in-depth video analysis. Given a long highlight video (8-10 minutes) of a particular player, the model needs to predict the skill level (e.g., excellent, good, average, fair, poor) for each of the 20 basketball skills. Our empirical analysis reveals that the current state-of-the-art video models struggle with this task, significantly lagging behind the human baseline. We believe that Basket could be a useful resource for developing new video models with advanced long-range, fine-grained recognition capabilities. In addition, we hope that our dataset will be useful for domain-specific applications such as fair basketball scouting, personalized player development, and many others. Dataset and code are available at https://github.com/yulupan00/BASKET.

Long-form video understanding is complicated by the high redundancy of video data and the abundance of query-irrelevant information. To tackle these challenges, we propose VideoTree, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM reasoning over long-form videos. First, VideoTree extracts query-relevant information from the input video through an iterative process, progressively refining the selection of keyframes based on their relevance to the query. Furthermore, VideoTree leverages the inherent hierarchical structure of long video data, which is often overlooked by existing LLM-based methods. Specifically, we incorporate multi-granularity information into a tree-based representation, allowing VideoTree to extract query-relevant details from long videos in a coarse-to-fine manner. This enables the model to effectively handle a wide range of video queries with varying levels of detail. Finally, VideoTree aggregates the hierarchical query-relevant information within the tree structure and feeds it into an LLM reasoning model to answer the query. Our experiments show that our method improves both reasoning accuracy and efficiency. Specifically, VideoTree outperforms existing training-free approaches on EgoSchema and NExT-QA with less inference time, achieving 61.1% and 75.6% accuracy on the test set without additional video-specific training. Moreover, on the long split of Video-MME (average 44 minutes), VideoTree achieves better performance than GPT-4V and many other MLLMs that were extensively trained on video data.

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and finetuning remain significant challenges.These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale.To address this, we present VIDEO-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-efficient RL with a video-adaptive test-time scaling (TTS) strategy.Building on observations about the data scaling, we skip the resource-intensive SFT step and employ efficient pure-RL training with outputbased rewards, requiring no additional annotations or extensive fine-tuning.Furthermore, to utilize computational resources more efficiently, we introduce a sparse-to-dense video TTS strategy that improves inference by iteratively adding frames based on output consistency.We validate our approach on multiple video reasoning benchmarks, showing that VIDEO-RTS surpasses existing video reasoning models by 2.4% in accuracy using only 3.6% training samples.Specifically, VIDEO-RTS achieves a 4.2% improvement on Video-Holmes, a recent and challenging video reasoning benchmark.Notably, our pure RL training and adaptive video TTS offer complementary strengths, enabling VIDEO-RTS's strong reasoning performance.(b) Video-RTS (Ours) (a) Video-R1 Qwen 2.5 VL Video-QA Data (6K) Video-Question input (Test-time Scaling) Training.Reinforcement Learning Inference.Sparse-to-Dense Video TTS 🔥 Training Stage 1. Supervised Fine-tuning Qwen 2.5 VL Vision-CoT Data (165K) Qwen 2.5 VL-SFT Training Stage 2. Reinforcement Learning Vision-Question Data (260K) Temporal-Augmented & Length-Based Reward Cross-Entropy Loss

Vision-language-action (VLA) models present a promising paradigm by training policies directly on real robot datasets like Open X-Embodiment. However, the high cost of real-world data collection hinders further data scaling, thereby restricting the generalizability of VLAs. In this paper, we introduce ReBot, a novel real-to-sim-to-real approach for scaling real robot datasets and adapting VLA models to target domains, which is the last-mile deployment challenge in robot manipulation. Specifically, ReBot replays real-world robot trajectories in simulation to diversify manipulated objects (real-to-sim), and integrates the simulated movements with inpainted real-world background to synthesize physically realistic and temporally consistent robot videos (sim-to-real). Our approach has several advantages: 1) it enjoys the benefit of real data to minimize the sim-to-real gap; 2) it leverages the scalability of simulation; and 3) it can generalize a pretrained VLA to a target domain with fully automated data pipelines. Extensive experiments in both simulation and real-world environments show that ReBot significantly enhances the performance and robustness of VLAs. For example, in SimplerEnv with the WidowX robot, ReBot improved the in-domain performance of Octo by 7.2% and OpenVLA by 21.8%, and out-of-domain generalization by 19.9% and 9.4%, respectively. For real-world evaluation with a Franka robot, ReBot increased the success rates of Octo by 17% and OpenVLA by 20%. More information can be found at our project page.

We present ExAct, a new video-language benchmark for expert-level understanding of skilled physical human activities. Our new benchmark contains 3,521 expert-curated video question-answer pairs spanning 11 physical activities in 6 domains: Sports, Bike Repair, Cooking, Health, Music, and Dance. ExAct requires the correct answer to be selected from five carefully designed candidate options, thus necessitating a nuanced, fine-grained, expert-level understanding of physical human skills. Evaluating the recent state-of-the-art VLMs on ExAct reveals a substantial performance gap relative to human expert performance. Specifically, the best-performing Gemini 2.5 Pro model achieves only 55.35% accuracy, well below the 82.02% attained by trained human experts. We believe that ExAct will be beneficial for developing and evaluating VLMs capable of precise understanding of human skills in various physical and procedural domains. Dataset and code are available at https://texaser.github.io/exactprojectpage/.

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model’s capacity to self-correct and adapt in complex scenarios. Recent efforts have attempted to address this limitation by incorporating reward models and reinforcement learning to enhance reasoning, or by employing tool-agent frameworks. However, these approaches face several challenges, including high annotation costs, reward signals that fail to capture real-time reasoning states, and low inference efficiency. To overcome these issues, we propose ReAgent-V, a novel agentic video understanding framework that integrates efficient frame selection with real-time reward generation during inference. These reward signals not only guide iterative answer refinement through a multi-perspective reflection mechanism—adjusting predictions from conservative, neutral, and aggressive viewpoints—but also enable automatic filtering of high-quality data for supervised fine-tuning (SFT), direct preference optimization (DPO), and group relative policy optimization (GRPO). ReAgent-V is lightweight, modular, and extensible, supporting flexible tool integration tailored to diverse tasks. Extensive experiments on 12 datasets across three core applications—video understanding, video reasoning enhancement, and vision-language-action model alignment—demonstrate significant gains in generalization and reasoning, with improvements of up to 6.9%, 2.1%, and 9.8%, respectively, highlighting the effectiveness and versatility of the proposed framework.

We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named Dam, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our Dam model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend Dam to continual image classification and image QA and outperform prior methods by a large margin. The code will be publicly released.

We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos accompanied by background music. This enables our model to learn to generate realistic and diverse music. To accomplish this goal, we develop a generative video-music Transformer with a novel semantic video-music alignment scheme. Our model uses a joint autoregressive and contrastive learning objective, which encourages the generation of music aligned with high-level video content. We also introduce a novel video-beat alignment scheme to match the generated music beats with the low-level motions in the video. Lastly, to capture fine-grained visual cues in a video needed for realistic background music generation, we introduce a new temporal video encoder architecture, allowing us to efficiently process videos consisting of many densely sampled frames. We train our frame-work on our newly curated DISCO-MV dataset, consisting of 2.2M video-music samples, which is orders of magnitude larger than any prior datasets used for video music generation. Our method outperforms existing approaches on the DISCO-MV and MusicCaps datasets according to various music generation evaluation metrics, including human evaluation. Results are available at https://genjib.github.io/project_page/VMAs/index.html

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/

Xiyao Wang, Yuhang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Fuxiao Liu, Gedas Bertasius, Mohit Bansal, Huaxiu Yao, Furong Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

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.

Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different temporal granularities. We propose Video ReCap, a recursive video captioning model that can process video inputs of dramatically different lengths (from 1 second to 2 hours) and output video captions at multiple hierarchy levels. The recursive video-language architecture exploits the synergy between different video hierarchies and can process hour-long videos efficiently. We utilize a curriculum learning training scheme to learn the hierarchical structure of videos, starting from clip-level captions describing atomic actions, then focusing on segment-level descriptions, and concluding with generating summaries for hour-long videos. Furthermore, we introduce Ego4D-HCap dataset by augmenting Ego4D with 8,267 manually collected long-range video summaries. Our recursive model can flexibly generate captions at different hierarchy levels while also being useful for other complex video understanding tasks, such as VideoQA on EgoSchema. Data, code, and models are publicly available at https://sites.google.com/view/vidrecap.

Active Speaker Detection (ASD) aims to identify who is speaking in each frame of a video. Solving ASD involves using audio and visual information in two complementary contexts: long-term intra-speaker context models the temporal dependencies of the same speaker, while short-term inter-speaker context models the interactions of speakers in the same scene. Motivated by these observations, we propose LoCoNet, a simple but effective Long-Short Context Network that leverages Long-term Intra-speaker Modeling (LIM) and Short-term Inter-speaker Modeling (SIM) in an interleaved manner. LIM employs self-attention for long-range temporal dependencies modeling and cross-attention for audio-visual interactions modeling. SIM incorporates convolutional blocks that capture local patterns for short-term inter-speaker context. Experiments show that LoCoNet achieves state-of-the-art performance on multiple datasets, with 95.2% (+0.3%) mAP on AVA-ActiveSpeaker, 97.2% (+2.7%) mAP on Talkies, and 68.4% (+7.7%) mAP on Ego4D. Moreover, in challenging cases where multiple speakers are present, LoCoNet outperforms previous state-of-the-art methods by 3.0% mAP on AVA-ActiveSpeaker. The code is available at https://github.com/SJTUwxz/LoCoNet_ASD.

We present LLoVi, a simple yet effective Language-based Long-range Video question-answering (LVQA) framework. Our method decomposes the short- and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual captioner to generate textual descriptions of short video clips (0.5-8 seconds in length) densely sampled from a long input video. Afterward, an LLM aggregates the densely extracted short-term captions to answer a given question. Furthermore, we propose a novel multi-round summarization prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question. To analyze what makes our simple framework so effective, we thoroughly evaluate various components of our framework. Our empirical analysis reveals that the choice of the visual captioner and LLM is critical for good LVQA performance. The proposed multi-round summarization prompt also leads to a significant LVQA performance boost. Our method achieves the best-reported results on the EgoSchema dataset, best known for very long-form video question-answering. LLoVi also outperforms the previous state-of-the-art by 10.2% and 6.2% on NExT-QA and IntentQA for LVQA. Finally, we extend LLoVi to grounded VideoQA, which requires both QA and temporal localization, and show that it outperforms all prior methods on NExT-GQA. Code is available at https://github.com/CeeZh/LLoVi.

Robot Imitation Learning (IL) is a crucial technique in robot learning, where agents learn by mimicking human demonstrations. However, IL encounters scalability challenges stemming from both non-user-friendly demonstration collection methods and the extensive time required to amass a sufficient number of demonstrations for effective training. In response, we introduce the Augmented Reality for Collection and generAtion of DEmonstrations (ARCADE) framework, designed to scale up demonstration collection for robot manipulation tasks. Our framework combines two key capabilities: 1) it leverages AR to make demonstration collection as simple as users performing daily tasks using their hands, and 2) it enables the automatic generation of additional synthetic demonstrations from a single human-derived demonstration, significantly reducing user effort and time. We assess ARCADE’s performance on a real Fetch robot across three robotics tasks: 3-Waypoints-Reach, Push, and Pick-And-Place. Using our framework, we were able to rapidly train a policy using vanilla Behavioral Cloning (BC), a classic IL algorithm, which excelled across these three tasks. We also deploy ARCADE on a real household task, Pouring-Water, achieving an 80% success rate.

The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.

The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This contrasts with most existing video recognition models, which are typically designed for short-range video analysis. This work proposes a State-Space Transformer model that can efficiently capture dependencies in long movie videos for accurate movie scene detection. Our model, called TranS4mer, is built using a novel S4A building block, combining the strengths of structured state-space sequence (S4) and self-attention (A) layers. Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies. Afterward, the state-space operation in the S4A block aggregates long-range inter-shot cues. The final TranS4mer model, which can be trained end-to-end, is obtained by stacking the S4A blocks one after the other multiple times. Our proposed TranS4mer outperforms all prior methods in three movie scene detection datasets, including MovieNet, BBC, and OVSD, while being 2× faster and requiring 3× less GPU memory than standard Transformer models. We will release our code and models.

Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT. To efficiently fuse visual and audio cues, our LAVISH adapter uses a small set of latent tokens, which form an attention bottleneck, thus, eliminating the quadratic cost of standard cross-attention. Compared to the existing modality-specific audio-visual methods, our approach achieves competitive or even better performance on various audio-visual tasks while using fewer tunable parameters and without relying on costly audio pretraining or external audio encoders. Our code is available at https://genjib.github.io/project_page/LAVISH/

Click-based interactive image segmentation aims at extracting objects with a limited user clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently, the plain, non-hierarchical Vision Transformer (ViT) has emerged as a competitive backbone for dense prediction tasks. This design allows the original ViT to be a foundation model that can be finetuned for downstream tasks without redesigning a hierarchical backbone for pretraining. Although this design is simple and has been proven effective, it has not yet been explored for interactive image segmentation. To fill this gap, we propose SimpleClick, the first interactive segmentation method that leverages a plain backbone. Based on the plain backbone, we introduce a symmetric patch embedding layer that encodes clicks into the backbone with minor modifications to the backbone itself. With the plain backbone pretrained as a masked autoencoder (MAE), SimpleClick achieves state-of-the-art performance. Remarkably, our method achieves 4.15 NoC@90 on SBD, improving 21.8% over the previous best result. Extensive evaluation on medical images demonstrates the generalizability of our method. We provide a detailed computational analysis, highlighting the suitability of our method as a practical annotation tool.

The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and low-level (object) visual clues and how they relate to the text query. To this end, we propose a Unified Coarse-to-fine Alignment model, dubbed UCoFiA. Specifically, our model captures the cross-modal similarity information at different granularity levels. To alleviate the effect of irrelevant visual clues, we also apply an Interactive Similarity Aggregation module (ISA) to consider the importance of different visual features while aggregating the cross-modal similarity to obtain a similarity score for each granularity. Finally, we apply the Sinkhorn-Knopp algorithm to normalize the similarities of each level before summing them, alleviating over- and under-representation issues at different levels. By jointly considering the cross-modal similarity of different granularity, UCoFiA allows the effective unification of multi-grained alignments. Empirically, UCoFiA outperforms previous state-of-the-art CLIP-based methods on multiple video-text retrieval benchmarks, achieving 2.4%, 1.4% and 1.3% improvements in text-to-video retrieval R@1 on MSR-VTT, Activity-Net, and DiDeMo, respectively. Our code is publicly available at https://github.com/Ziyang412/UCoFiA.

In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires not only recognizing the individual steps that compose the task but also capturing their temporal dependencies. This problem is dramatically different from traditional action classification, where models are typically optimized on videos that span only a few seconds and that are manually trimmed to contain simple atomic actions. While step annotations could enable the training of models to recognize the individual steps of procedural activities, existing large-scale datasets in this area do not include such segment labels due to the prohibitive cost of manually annotating temporal boundaries in long videos. To address this issue, we propose to automatically identify steps in instructional videos by leveraging the distant supervision of a textual knowledge base (wikiHow) that includes detailed descriptions of the steps needed for the execution of a wide variety of complex activities. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base. We demonstrate that video models trained to recognize these automatically-labeled steps (without manual supervision) yield a representation that achieves superior generalization performance on four downstream tasks: recognition of procedural activities, step classification, step forecasting and egocentric video classification.

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper, we empirically demonstrate that self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results that are on par or better than those obtained with supervised pretraining on large-scale image datasets, even massive ones such as ImageNet-21K. Since transformer-based models are effective at capturing dependencies over extended temporal spans, we propose a simple learning procedure that forces the model to match a long-term view to a short-term view of the same video. Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent. To demonstrate the generality of our findings, we implement and validate our approach under three different self-supervised contrastive learning frameworks (MoCo v3, BYOL, SimSiam) using two distinct video-transformer architectures, including an improved variant of the Swin Transformer augmented with space-time attention. We conduct a thorough ablation study and show that LSTCL achieves competitive performance on multiple video benchmarks and represents a convincing alternative to supervised image-based pretraining.

The majority of traditional text-to-video retrieval systems operate in static environments, i.e., there is no interaction between the user and the agent beyond the initial textual query provided by the user. This can be suboptimal if the initial query has ambiguities, which would lead to many falsely retrieved videos. To overcome this limitation, we propose a novel framework for Video Retrieval using Dialog (ViReD), which enables the user to interact with an AI agent via multiple rounds of dialog. The key contribution of our framework is a novel multimodal question generator that learns to ask questions that maximize the subsequent video retrieval performance. Our multimodal question generator uses (i) the video candidates retrieved during the last round of interaction with the user and (ii) the text-based dialog history documenting all previous interactions, to generate questions that incorporate both visual and linguistic cues relevant to video retrieval. Furthermore, to generate maximally informative questions, we propose an Information-Guided Supervision (IGS), which guides the question generator to ask questions that would boost subsequent video retrieval accuracy. We validate the effectiveness of our interactive ViReD framework on the AVSD dataset, showing that our interactive method performs significantly better than traditional non-interactive video retrieval systems. Furthermore, we also demonstrate that our proposed approach also generalizes to the real-world settings that involve interactions with real humans, thus, demonstrating the robustness and generality of our framework.

We present VX2TEXT, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme that enables end-to-end training. Furthermore, unlike prior encoder-only models, our network includes an autoregressive decoder to generate open-ended text from the multimodal embeddings fused by the language encoder. This renders our approach fully generative and makes it directly applicable to different "video+x to text" problems without the need to design specialized network heads for each task. The proposed framework is not only conceptually simple but also remarkably effective: experiments demonstrate that our approach based on a single architecture outperforms the state-of-the-art on three videobased text-generation tasks—captioning, question answering and audio-visual scene-aware dialog.

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named “TimeSformer,” adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Our experimental study compares different self-attention schemes and suggests that “divided attention,” where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically new design, TimeSformer achieves state-of-the-art results on several action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Finally, compared to 3D convolutional networks, our model is faster to train, it can achieve dramatically higher test efficiency (at a small drop in accuracy), and it can also be applied to much longer video clips (over one minute long). Code and models are available at: https://github.com/facebookresearch/TimeSformer.

A significant challenge in video understanding is posed by the high dimensionality of the input, which induces large computational cost and high memory footprints. Deep convolutional models operating on video apply pooling and striding to reduce feature dimensionality and to increase the receptive field. However, despite these strategies, modern approaches cannot effectively leverage spatiotemporal structure over long temporal extents. In this paper we introduce an approach that reduces a video of 10 seconds to a sparse graph of only 160 feature nodes such that efficient inference in this graph produces state-of-the-art accuracy on challenging action recognition datasets. The nodes of our graph are semantic supervoxels that capture the spatiotemporal structure of objects and motion cues in the video, while edges between nodes encode spatiotemporal relations and feature similarity. We demonstrate that a shallow network that interleaves graph convolution and graph pooling on this compact representation implements an effective mechanism of relational reasoning yielding strong recognition results on both Charades and Something-Something.

We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence. Our method, named MaskProp, adapts the popular Mask R-CNN to video by adding a mask propagation branch that propagates frame-level object instance masks from each video frame to all the other frames in a video clip. This allows our system to predict clip-level instance tracks with respect to the object instances segmented in the middle frame of the clip. Clip-level instance tracks generated densely for each frame in the sequence are finally aggregated to produce video-level object instance segmentation and classification. Our experiments demonstrate that our clip-level instance segmentation makes our approach robust to motion blur and object occlusions in video. MaskProp achieves the best reported accuracy on the YouTube-VIS dataset, outperforming the ICCV 2019 video instance segmentation challenge winner despite being much simpler and using orders of magnitude less labeled data (1.3M vs 1B images and 860K vs 14M bounding boxes). The project page is at: https://gberta.github.io/maskprop/.

Many objects in the real world undergo dramatic variations in visual appearance. For example, a tomato may be red or green, sliced or chopped, fresh or fried, liquid or solid. Training a single detector to accurately recognize tomatoes in all these different states is challenging. On the other hand, contextual cues (e.g., the presence of a knife, a cutting board, a strainer or a pan) are often strongly indicative of how the object appears in the scene. Recognizing such contextual cues is useful not only to improve the accuracy of object detection or to determine the state of the object, but also to understand its functional properties and to infer ongoing or upcoming human-object interactions. A fully-supervised approach to recognizing object states and their contexts in the real-world is unfortunately marred by the long-tailed, open-ended distribution of the data, which would effectively require massive amounts of annotations to capture the appearance of objects in all their different forms. Instead of relying on manually-labeled data for this task, we propose a new framework for learning Contextualized OBject Embeddings (COBE) from automatically-transcribed narrations of instructional videos. We leverage the semantic and compositional structure of language by training a visual detector to predict a contextualized word embedding of the object and its associated narration. This enables the learning of an object representation where concepts relate according to a semantic language metric. Our experiments show that our detector learns to predict a rich variety of contextual object information, and that it is highly effective in the settings of few-shot and zero-shot learning.

Modern approaches for multi-person pose estimation in video require large amounts of dense annotations. However, labeling every frame in a video is costly and labor intensive. To reduce the need for dense annotations, we propose a PoseWarper network that leverages training videos with sparse annotations (every k frames) to learn to perform dense temporal pose propagation and estimation. Given a pair of video frames---a labeled Frame A and an unlabeled Frame B---we train our model to predict human pose in Frame A using the features from Frame B by means of deformable convolutions to implicitly learn the pose warping between A and B. We demonstrate that we can leverage our trained PoseWarper for several applications. First, at inference time we can reverse the application direction of our network in order to propagate pose information from manually annotated frames to unlabeled frames. This makes it possible to generate pose annotations for the entire video given only a few manually-labeled frames. Compared to modern label propagation methods based on optical flow, our warping mechanism is much more compact (6M vs 39M parameters), and also more accurate (88.7% mAP vs 83.8% mAP). We also show that we can improve the accuracy of a pose estimator by training it on an augmented dataset obtained by adding our propagated poses to the original manual labels. Lastly, we can use our PoseWarper to aggregate temporal pose information from neighboring frames during inference. This allows us to obtain state-of-the-art pose detection results on PoseTrack2017 and PoseTrack2018 datasets.

We present a model that uses a single first-person image to generate an egocentric basketball motion sequence in the form of a 12D camera configuration trajectory, which encodes a player's 3D location and 3D head orientation throughout the sequence. To do this, we first introduce a future convolutional neural network (CNN) that predicts an initial sequence of 12D camera configurations, aiming to capture how real players move during a one-on-one basketball game. We also introduce a goal verifier network, which is trained to verify that a given camera configuration is consistent with the final goals of real one-on-one basketball players. Next, we propose an inverse synthesis procedure to synthesize a refined sequence of 12D camera configurations that (1) sufficiently matches the initial configurations predicted by the future CNN, while (2) maximizing the output of the goal verifier network. Finally, by following the trajectory resulting from the refined camera configuration sequence, we obtain the complete 12D motion sequence. Our model generates realistic basketball motion sequences that capture the goals of real players, outperforming standard deep learning approaches such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and generative adversarial networks (GANs).

Conditional random fields (CRFs) provide a powerful tool for structured prediction, but cast significant challenges in both the learning and inference steps. Approximation techniques are widely used in both steps, which should be considered jointly to guarantee good performance (a.k.a. “inferning"). Perturb-and-MAP models provide a promising alternative to CRFs, but require global combinatorial optimization and hence they are usable only on specific models. In this work, we present a new Local Perturb-and-MAP (locPMAP) framework that replaces the global optimization with a local optimization by exploiting our observed connection between locPMAP and the pseudolikelihood of the original CRF model. We test our approach on three different vision tasks and show that our method achieves consistently improved performance over other approximate inference techniques optimized to a pseudolikelihood objective. Additionally, we demonstrate that we can integrate our method in the fully convolutional network framework to increase our model’s complexity. Finally, our observed connection between locPMAP and the pseudolikelihood leads to a novel perspective for understanding and using pseudolikelihood.

Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has attempted to address this issue by post-processing predictions with CRFs or MRFs. But such models often fail to capture semantic relationships between objects, which causes spatially disjoint predictions. To overcome these problems, recent methods integrated CRFs or MRFs into an FCN framework. The downside of these new models is that they have much higher complexity than traditional FCNs, which renders training and testing more challenging. In this work we introduce a simple, yet effective Convolutional Random Walk Network (RWN) that addresses the issues of poor boundary localization and spatially fragmented predictions with very little increase in model complexity. Our proposed RWN jointly optimizes the objectives of pixelwise affinity and semantic segmentation. It combines these two objectives via a novel random walk layer that enforces consistent spatial grouping in the deep layers of the network. Our RWN is implemented using standard convolution and matrix multiplication. This allows an easy integration into existing FCN frameworks and it enables end-to-end training of the whole network via standard back-propagation. Our implementation of RWN requires just 131 additional parameters compared to the traditional FCNs, and yet it consistently produces an improvement over the FCNs on semantic segmentation and scene labeling.

A first-person camera, placed at a person's head, captures, which objects are important to the camera wearer. Most prior methods for this task learn to detect such important objects from the manually labeled first-person data in a supervised fashion. However, important objects are strongly related to the camera wearer's internal state such as his intentions and attention, and thus, only the person wearing the camera can provide the importance labels. Such a constraint makes the annotation process costly and limited in scalability. In this work, we show that we can detect important objects in first-person images without the supervision by the camera wearer or even third-person labelers. We formulate an important detection problem as an interplay between the 1) segmentation and 2) recognition agents. The segmentation agent first proposes a possible important object segmentation mask for each image, and then feeds it to the recognition agent, which learns to predict an important object mask using visual semantics and spatial features. We implement such an interplay between both agents via an alternating cross-pathway supervision scheme inside our proposed Visual-Spatial Network (VSN). Our VSN consists of spatial ("where") and visual ("what") pathways, one of which learns common visual semantics while the other focuses on the spatial location cues. Our unsupervised learning is accomplished via a cross-pathway supervision, where one pathway feeds its predictions to a segmentation agent, which proposes a candidate important object segmentation mask that is then used by the other pathway as a supervisory signal. We show our method's success on two different important object datasets, where our method achieves similar or better results as the supervised methods.

This paper presents a method to assess a basketball player's performance from his/her first-person video. A key challenge lies in the fact that the evaluation metric is highly subjective and specific to a particular evaluator. We leverage the first-person camera to address this challenge. The spatiotemporal visual semantics provided by a first-person view allows us to reason about the camera wearer's actions while he/she is participating in an unscripted basketball game. Our method takes a player's first-person video and provides a player's performance measure that is specific to an evaluator's preference. To achieve this goal, we first use a convolutional LSTM network to detect atomic basketball events from first-person videos. Our network's ability to zoom-in to the salient regions addresses the issue of a severe camera wearer's head movement in first-person videos. The detected atomic events are then passed through the Gaussian mixtures to construct a highly non-linear visual spatiotemporal basketball assessment feature. Finally, we use this feature to learn a basketball assessment model from pairs of labeled first-person basketball videos, for which a basketball expert indicates, which of the two players is better. We demonstrate that despite not knowing the basketball evaluator's criterion, our model learns to accurately assess the players in real-world games. Furthermore, our model can also discover basketball events that contribute positively and negatively to a player's performance.

The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the deep layers. As a result FCNs tend to produce segmentations that are poorly localized around object boundaries. Prior work has attempted to address this issue in post-processing steps, for example using a color-based CRF on top of the FCN predictions. However, these approaches require additional parameters and low-level features that are difficult to tune and integrate into the original network architecture. Additionally, most CRFs use colorbased pixel affinities, which are not well suited for semantic segmentation and lead to spatially disjoint predictions. To overcome these problems, we introduce a Boundary Neural Field (BNF), which is a global energy model integrating FCN predictions with boundary cues. The boundary information is used to enhance semantic segment coherence and to improve object localization. Specifically, we first show that the convolutional filters of semantic FCNs provide good features for boundary detection. We then employ the predicted boundaries to define pairwise potentials in our energy. Finally, we show that our energy decomposes semantic segmentation into multiple binary problems, which can be relaxed for efficient global optimization. We report extensive experiments demonstrating that minimization of our global boundary-based energy yields results superior to prior globalization methods, both quantitatively as well as qualitatively.

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that recognizing objects and predicting contours are two mutually related tasks. Contrary to traditional approaches, we show that we can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, we exploit object-related features as high-level cues for contour detection.

Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a boundary. Inspired by this observation, in this work we show how to predict boundaries by exploiting object-level features from a pretrained object-classification network. Our method can be viewed as a "High-for-Low" approach where high-level object features inform the low-level boundary detection process. Our model achieves state-of-the-art performance on an established boundary detection benchmark and it is efficient to run. Additionally, we show that due to the semantic nature of our boundaries we can use them to aid a number of high-level vision tasks. We demonstrate that using our boundaries we improve the performance of state-of-the-art methods on the problems of semantic boundary labeling, semantic segmentation and object proposal generation. We can view this process as a "Low-for-High'" scheme, where low-level boundaries aid high-level vision tasks. Thus, our contributions include a boundary detection system that is accurate, efficient, generalizes well to multiple datasets, and is also shown to improve existing state-of-the-art high-level vision methods on three distinct tasks.