CVPR 2025 Papers

Due to the interference of background noise, existing video anomaly detection methods are prone to detect some normal events in complex scenes as anomalies. Meanwhile, we note that the diversity of normal patterns has not been adequately considered, i.e., the normal events that are worthy of reference in the test data have not been properly utilized, which raises the risk of missed and false detections. In this work, we combine the tasks of next-frame prediction and predicted-frame reconstruction to propose a noise-resistant video anomaly detection method. For the prediction task, we develop an RGB Error-Guided Multiscale Predictive Coding (EG-MPC) framework to overcome the interference of background noise on the learning of appearance and motion features of objects at various scales, thus achieving high-quality frame prediction. For the reconstruction task, we introduce the Dynamic Memory Modules (DMMs) into the reconstruction network, and design sparse aggregation and selective update strategies for the memory items in the DMMs to effectively represent diverse normal patterns while increasing the difficulty of reconstructing anomalies, thus making it easier to distinguish between normal and abnormal frames. Extensive experiments on four benchmark datasets demonstrate that our proposed method outperforms state-of-the-art approaches, especially in complex scenarios.

Efficient video coding is highly dependent on exploiting the temporal redundancy, which is usually achieved by extracting and leveraging the temporal context in the emerging conditional coding-based neural video codec (NVC). Although the latest NVC has achieved remarkable progress in improving the compression performance, the inherent temporal context propagation mechanism lacks the ability to sufficiently leverage the reference information, limiting further improvement. In this paper, we address the limitation by modulating the temporal context with the reference frame in two steps. Specifically, we first propose the flow orientation to mine the inter-correlation between the reference frame and prediction frame for generating the additional oriented temporal context. Moreover, we introduce the context compensation to leverage the oriented context to modulate the propagated temporal context generated from the propagated reference feature. Through the synergy mechanism and decoupling loss supervision, the irrelevant propagated information can be effectively eliminated to ensure better context modeling. Experimental results demonstrate that our codec achieves on average 22.7% bitrate reduction over the advanced traditional video codec H.266/VVC, and offers an average 10.1% bitrate saving over the previous state-of-the-art NVC DCVC-FM. The code is available at https://github.com/Austin4USTC/DCMVC.

Efficiently retrieving and synthesizing information from large-scale multimodal collections has become a critical challenge. However, existing video retrieval datasets suffer from scope limitations, primarily focusing on matching descriptive but vague queries with small collections of professionally edited, English-centric videos. To address this gap, we introduce MultiVENT 2.0, a large-scale, multilingual event-centric video retrieval benchmark featuring a collection of more than 218,000 news videos and over 3,900 queries targeting specific world events. These queries specifically target information found in the visual content, audio, embedded text, and text metadata of the videos, requiring systems leverage all these sources to succeed at the task. Preliminary results show that state-of-the-art vision-language models struggle significantly with this task, and while alternative approaches show promise, they are still insufficient to adequately address this problem. These findings underscore the need for more robust multimodal retrieval systems, as effective video retrieval is a crucial step towards multimodal content understanding and generation.

Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist--a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt with cross-attention layers. Developing such a large model presents two main challenges: dataset and evaluation. First, as paired datasets of reference images and videos are extremely hard to collect, we sample selected video frames as reference images and synthesize a clip of the target video. However, while models can easily denoise training videos given reference frames, they fail to generalize to new contexts. To mitigate this issue, we design a new automatic data construction pipeline with extensive image augmentations. Second, evaluating open-set video personalization is a challenge in itself. To address this, we introduce a personalization benchmark that focuses on accurate subject fidelity and supports diverse personalization scenarios. Finally, our extensive experiments show that our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.

Recent advancements in video generation models, such as Stable Video Diffusion, have shown promising results, but these works primarily focus on short videos, often limited to a single scene and lacking a rich storyline. These models struggle with generating long videos that involve multiple scenes, coherent narratives, and consistent characters. Furthermore, there is currently no publicly accessible dataset specifically designed for analyzing, evaluating, and training models for long video generation. In this paper, we present MovieBench: A Hierarchical Movie-Level Dataset for Long Video Generation, which addresses these challenges by providing unique contributions: (1) character consistency across scenes, (2) long videos with rich and coherent storylines, and (3) multi-scene narratives. MovieBench features three distinct levels of annotation: the movie level, which provides a broad overview of the film; the scene level, offering a mid-level understanding of the narrative; and the shot level, which emphasizes specific moments with detailed descriptions.

Video personalization, which generates customized videos using reference images, has gained significant attention.However, prior methods typically focus on single-concept personalization, limiting broader applications that require multi-concept integration.Attempts to extend these models to multiple concepts often lead to identity blending, which results in composite characters with fused attributes from multiple sources.This challenge arises due to the lack of a mechanism to link each concept with its specific reference image.We address this with anchored prompts, which embed image anchors as unique tokens within text prompts, guiding accurate referencing during generation.Additionally, we introduce concept embeddings to encode the order of reference images.Our approach, Movie Weaver, seamlessly weaves multiple concepts--including face, body, and animal images--into one video, allowing flexible combinations in a single model.The evaluation shows that Movie Weaver outperforms existing methods for multi-concept video personalization in identity preservation and overall quality.

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs in processing sequential visual data is still insufficiently explored, highlighting the absence of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including sub- titles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. 900 videos with a total of 254 hours are manually selected and annotated by repeatedly viewing all the video content, resulting in 2,700 question-answer pairs. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1.5 Pro, as well as open-source image models like InternVL-Chat-V1.5 and video models like LLaVA-NeXT-Video. Our experiments reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models with an average accuracy of 75%, compared to 71.9% for GPT-4o. The results also demonstrate that Video-MME is a universal benchmark, which applies to both image and video MLLMs. Further analysis indicates that subtitle and audio information could significantly enhance video understanding. Besides, a decline in MLLM performance is observed as video duration increases for all models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data, shedding light on future MLLM development. Project page: https://video-mme.github.io.

In this paper, we introduce Motion-Grounded Video Reasoning, a new motionunderstanding task that requires generating visual answers (video segmentationmasks) according to the input question, and hence needs implicit spatiotemporalreasoning and grounding. This task extends existing spatiotemporal groundingwork focusing on explicit action/motion grounding, to a more general format byenabling implicit reasoning via questions. To facilitate the development of the newtask, we collect a large-scale dataset called GROUNDMORE, which comprises1,715 video clips, 249K object masks that are deliberately designed with 4 questiontypes (Causal, Sequential, Counterfactual, and Descriptive) for benchmarkingdeep and comprehensive motion reasoning abilities. GROUNDMORE uniquelyrequires models to generate visual answers, providing a more concrete and visuallyinterpretable response than plain texts. It evaluates models on both spatiotemporalgrounding and reasoning, fostering to address complex challenges in motion-relatedvideo reasoning, temporal perception, and pixel-level understanding. Furthermore,we introduce a novel baseline model named Motion-Grounded Video ReasoningAssistant (MORA). MORA incorporates the multimodal reasoning ability from theMultimodal LLM, the pixel-level perception capability from the grounding model(SAM), and the temporal perception ability from a lightweight localization head.MORA achieves respectable performance on GROUNDMORE outperforming thebest existing visual grounding baseline model by an average of 21.5% relatively.We hope this novel and challenging task will pave the way for future advancementsin robust and general motion understanding via video reasoning segmentation.

Visual-Language Tracking (VLT) is emerging as a promising paradigm to bridge the human-machine performance gap. For single objects, VLT broadens the problem scope to text-driven video comprehension. Yet, this direction is still confined to 2D spatial extents, currently lacking the ability to deal with 3D tracking in the confines of monocular video. Unfortunately, advances in 3D tracking mainly rely on expensive sensor inputs, e.g., point clouds, depth measurements, radar. Absence of language counterpart for the outputs of these mildly democratized sensors in the literature also hinders VLT expansion to 3D tracking. Addressing that, we make the first attempt towards extending VLT to 3D tracking based on monocular video. We present a comprehensive framework, introducing (i) the Monocular-Video-based 3D Visual Language Tracking (Mono3DVLT) task, (ii) a large-scale dataset for the task, called Mono3DVLT-V2X, and (iii) a customized neural model for the task. Our dataset is carefully curated, leveraging a Large Langauge Model (LLM) followed by human verification, composing natural language descriptions for 79,158 video sequences aiming at single object tracking, providing 2D and 3D bounding box annotations. Our neural model, termed Mono3DVLT-MT, is the first targeted approach for the Mono3DVLT task. Comprising the pipeline of multi-modal feature extractor, visual-language encoder, tracking decoder and a tracking head, our model sets a strong baseline for the task on Mono3DVLT-V2X. Experimental results show that our method significantly outperforms existing techniques on the Mono3DVLT-V2X dataset. Our dataset and code are available in https://github.com/hongkai-wei/Mono3DVLT.

Traditional video instance segmentation (VIS) models rely on extensive per-frame video annotations, which are both time-consuming and costly. In this paper, we present MinMaxVIS, a novel VIS framework that reduces the dependency on fully labeled video datasets by utilizing a small set of labeled images from the target domain along with a large volume of general-domain, unlabeled images. MinMaxVIS operates in three stages: first, a preliminary segmentation model is trained on the small labeled set from the target domain; this model then retrieves relevant instances from the unlabeled dataset to build a high-quality pseudo-labeled set, ensuring a rich content alignment with the target domain while avoiding the inefficiencies of large-scale semi-supervised learning across the entire unlabeled set. Finally, we train MinMaxVIS on a combination of labeled and pseudo-labeled data, addressing challenges such as noise in pseudo-labels and instance association across frames. To simulate object continuity, we augment static images to create paired frames, allowing MinMaxVIS to capture instance associations effectively. MinMaxVIS outperforms the prior image-driven approach, MinVIS, achieving superior mAP scores with significantly reduced labeled data. For instance, MinMaxVIS with a Swin-L backbone attains 62.2 mAP on YouTube-VIS 2019 using only 2% labeled data and additional unlabeled images from SA-1B. This surpasses MinVIS, which uses the same backbone trained on fully labeled YouTube-VIS 2019, by 0.6 mAP.

Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a time. To enable time-aware interactions between event captions and video tokens, we design a time-based positional encoding method, dubbed ReRoPE. This encoding helps to guide the cross-attention operation. By fine-tuning a pre-trained video diffusion transformer on temporally grounded data, our approach produces coherent videos with smoothly connected events. For the first time in the literature, our model offers control over the timing of events in generated videos. Extensive experiments demonstrate that MinT outperforms existing commercial and open-source models by a large margin.

Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features from text encoders yet struggle with limited text comprehension. The recent success of large language models (LLMs) showcases the power of decoder-only transformers, which offers three clear benefits for text-to-video (T2V) generation, namely, precise text understanding resulting from the superior scalability, imagination beyond the input text enabled by next token prediction, and flexibility to prioritize user interests through instruction tuning. Nevertheless, the feature distribution gap emerging from the two different text modeling paradigms hinders the direct use of LLMs in established T2V models. This work addresses this challenge with Mimir, an end-to-end training framework featuring a carefully tailored token fuser to harmonize the outputs from text encoders and LLMs. Such a design allows the T2V model to fully leverage learned video priors while capitalizing on the text-related capability of LLMs. Extensive quantitative and qualitative results demonstrate the effectiveness of our approach in generating high-quality videos with excellent text comprehension, especially when processing short captions and managing shifting motions. The code and models will be made publicly available.

Auxiliary-free human video matting methods, which rely solely on input frames, often struggle with complex or ambiguous backgrounds. To tackle this, we propose MatAnyone, a practical framework designed for target-assigned video matting. Specifically, building on a memory-based framework, we introduce a consistent memory propagation module via region-adaptive memory fusion, which adaptively combines memory from the previous frame. This ensures stable semantic consistency in core regions while maintaining fine details along object boundaries. For robust training, we present a larger, high-quality, and diverse dataset for video matting. Additionally, we incorporate a novel training strategy that efficiently leverages large-scale segmentation data, further improving matting stability. With this new network design, dataset, and training strategy, MatAnyone delivers robust, accurate video matting in diverse real-world scenarios, outperforming existing methods. The code and model will be publicly available.

Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene understanding, self-supervised methods are typically only used as a weight initialization step for task-specific fine-tuning, limiting their utility for general-purpose feature extraction. This paper aims to address this shortcoming by proposing a robust evaluation protocol specifically designed to assess the quality of self-supervised features for 3D scene understanding. Our protocol uses multi-resolution feature sampling of hierarchical models to create rich point-level representations that capture the semantic capabilities of the model and, hence, are suitable for evaluation with linear probing and nearest-neighbor methods. Furthermore, we introduce the first self-supervised model that performs similarly to supervised models when only off-the-shelf features are used in a linear probing setup. In particular, our model is trained natively in 3D with a novel self-supervised approach based on a Masked Scene Modeling objective, which reconstructs deep features of masked patches in a bottom-up manner and is specifically tailored to hierarchical 3D models. Our experiments not only demonstrate that our method achieves competitive performance to supervised models, but also surpasses existing self-supervised approaches by a large margin.

World models that forecast environmental changes from actions are vital for autonomous driving models with strong generalization. The prevailing driving world model mainly build on pixel-level video prediction model. Although these models can produce high-fidelity video sequences with advanced diffusion-based generator, they are constrained by their predictive duration and overall generalization capabilities. In this paper, we explore to solve this problem by combining pixel-level generation loss with MAE-style feature-level context learning. In particular, we instantiate this target with three key design: (1) A more scalable Diffusion Transformer (DiT) structure trained with extra mask construction task. (2) we devise diffusion-related mask tokens to deal with the fuzzy relations between mask reconstruction and generative diffusion process. (3) we extend mask construction task to spatial-temporal domain by utilizing row-wise mask for shifted self-attention rather than masked self-attention in MAE. Then, we adopt a row-wise cross-view module to align with this mask design. Based on above improvement, we propose MaskGWM: a Generalizable driving World Model embodied with Video Mask reconstruction. Our model contains two variants: MaskGWM-long, focusing on long-horizon prediction, and MaskGWM-mview, dedicated to multi-view generation.Comprehensive experiments on standard benchmarks validate the effectiveness of the proposed method, which contain normal validation of Nuscene dataset, long-horizon rollout of OpenDV-2K dataset and zero-shot validation of Waymo dataset. Quantitative metrics on these datasets show our method notably improving state-of-the-art driving world model.

In this paper, we introduce ManiVideo, a novel method for generating consistent and temporally coherent bimanual hand-object manipulation videos from given motion sequences of hands and objects. The core idea of ManiVideo is the construction of a multi-layer occlusion (MLO) representation that learns 3D occlusion relationships from occlusion-free normal maps and occlusion confidence maps. By embedding the MLO structure into the UNet in two forms, the model enhances the 3D consistency of dexterous hand-object manipulation. To further achieve the generalizable grasping of objects, we integrate Objaverse, a large-scale 3D object dataset, to address the scarcity of video data, thereby facilitating the learning of extensive object consistency. Additionally, we propose an innovative training strategy that effectively integrates multiple datasets, supporting downstream tasks such as human-centric hand-object manipulation video generation. Through extensive experiments, we demonstrate that our approach not only achieves video generation with plausible hand-object interaction and generalizable objects, but also outperforms existing SOTA methods.

Monitoring wildlife is essential for ecology and ethology, especially in light of the increasing human impact on ecosystems. Camera traps have emerged as habitat-centric sensors enabling the study of wildlife populations at scale with minimal disturbance. However, the lack of annotated video datasets limits the development of powerful video understanding models needed to process the vast amount of fieldwork data collected. To advance research in wild animal behavior monitoring we present MammAlps, a multimodal and multi-view dataset of wildlife behavior monitoring from 9 camera-traps in the Swiss National Park. MammAlps contains over 14 hours of video with audio, 2D segmentation maps and 8.5 hours of individual tracks densely labeled for species and behavior. Based on 6135 single animal clips, we propose the first hierarchical and multimodal animal behavior recognition benchmark using audio, video and reference scene segmentation maps as inputs. Furthermore, we also propose a second ecology-oriented benchmark aiming at identifying activities, species, number of individuals and meteorological conditions from 397 multi-view and long-term ecological events, including false positive triggers. We advocate that both tasks are complementary and contribute to bridging the gap between machine learning and ecology. Code and data are available at: https://github.com/eceo-epfl/MammAlps

Intelligent robots need to interact with diverse objects across various environments. The appearance and state of objects frequently undergo complex transformations depending on the object properties, e.g., phase transitions. However, in the vision community, segmenting dynamic objects with phase transitions is overlooked. In light of this, we introduce the concept of phase in segmentation, which categorizes real-world objects based on their visual characteristics and potential morphological and appearance changes. Then, we present a new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M^3-VOS), to verify the ability of models to understand object phases, which consists of 471 high-resolution videos spanning over 10 distinct everyday scenarios. It provides dense instance mask annotations that capture both object phases and their transitions. We evaluate state-of-the-art methods on M^3-VOS, yielding several key insights. Notably, current appearance-based approaches show significant room for improvement when handling objects with phase transitions. The inherent changes in disorder suggest that the predictive performance of the forward entropy-increasing process can be improved through a reverse entropy-reducing process. These findings lead us to propose ReVOS, a new plug-and-play model that improves its performance by reversal refinement. Our data and code will be publicly available at https://zixuan-chen.github.io/M-cube-VOS.github.io/.