Mavors: Multi-granularity Video Representation for Multimodal Large Language Model

• URL: http://arxiv.org/abs/2504.10068v1
• Date: Mon, 14 Apr 2025 10:14:44 GMT
• Title: Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
• Authors: Yang Shi, Jiaheng Liu, Yushuo Guan, Zhenhua Wu, Yuanxing Zhang, Zihao Wang, Weihong Lin, Jingyun Hua, Zekun Wang, Xinlong Chen, Bohan Zeng, Wentao Zhang, Fuzheng Zhang, Wenjing Yang, Di Zhang,
• Abstract summary: $mathbfMavors$ is a novel framework for holistic longvideo modeling.<n>Mavors encodes raw video content into latent representations through two core components.<n>The framework unifies image and video understanding by treating images as single-frame videos.
• Score: 39.24524388617938
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spatio-temporal patterns. Existing approaches (e.g., sparse sampling, dense sampling with low resolution, and token compression) suffer from significant information loss in temporal dynamics, spatial details, or subtle interactions, particularly in videos with complex motion or varying resolutions. To address this, we propose $\mathbf{Mavors}$, a novel framework that introduces $\mathbf{M}$ulti-gr$\mathbf{a}$nularity $\mathbf{v}$ide$\mathbf{o}$ $\mathbf{r}$epre$\mathbf{s}$entation for holistic long-video modeling. Specifically, Mavors directly encodes raw video content into latent representations through two core components: 1) an Intra-chunk Vision Encoder (IVE) that preserves high-resolution spatial features via 3D convolutions and Vision Transformers, and 2) an Inter-chunk Feature Aggregator (IFA) that establishes temporal coherence across chunks using transformer-based dependency modeling with chunk-level rotary position encodings. Moreover, the framework unifies image and video understanding by treating images as single-frame videos via sub-image decomposition. Experiments across diverse benchmarks demonstrate Mavors' superiority in maintaining both spatial fidelity and temporal continuity, significantly outperforming existing methods in tasks requiring fine-grained spatio-temporal reasoning.

Related papers

• Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition [6.168286187549952]
  We propose a hybrid end-to-end framework that factorizes learning across three key concepts to reduce inference cost by $330times$ versus prior art. Experiments show that our method results in a lightweight architecture achieving state-of-the-art video recognition performance.
  arXiv  Detail & Related papers  (2025-03-17T21:13:48Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [3.7270979204213446]
  We present four key contributions to address the challenges of video processing.<n>First, we introduce the 3D Inverted Vector-Quantization Variencoenco Autocoder.<n>Second, we present MotionAura, a text-to-video generation framework.<n>Third, we propose a spectral transformer-based denoising network.<n>Fourth, we introduce a downstream task of Sketch Guided Videopainting.
  arXiv  Detail & Related papers  (2024-10-10T07:07:56Z)
• SIGMA:Sinkhorn-Guided Masked Video Modeling [69.31715194419091]
  Sinkhorn-guided Masked Video Modelling ( SIGMA) is a novel video pretraining method. We distribute features of space-time tubes evenly across a limited number of learnable clusters. Experimental results on ten datasets validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations.
  arXiv  Detail & Related papers  (2024-07-22T08:04:09Z)
• Segmenting the motion components of a video: A long-term unsupervised model [5.801044612920816]
  We want to provide a coherent and stable motion segmentation over the video sequence. We propose a novel long-term optical-temporal model operating in a totally unsupervised way. We report experiments on four VOS, demonstrating competitive quantitative results.
  arXiv  Detail & Related papers  (2023-10-02T09:33:54Z)
• SViTT: Temporal Learning of Sparse Video-Text Transformers [65.93031164906812]
  We propose SViTT, a sparse video-text architecture that performs multi-frame reasoning with significantly lower cost than naive transformers with dense attention. SViTT employs two forms of sparsity: edge sparsity that limits the query-key communications between tokens in self-attention, and sparsity that discards uninformative visual tokens.
  arXiv  Detail & Related papers  (2023-04-18T08:17:58Z)
• Temporally Consistent Transformers for Video Generation [80.45230642225913]
  To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. No established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. We introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time.
  arXiv  Detail & Related papers  (2022-10-05T17:15:10Z)
• Multi-Attention Network for Compressed Video Referring Object Segmentation [103.18477550023513]
  Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented. This may hamper its application in real-world computing resource limited scenarios, such as autonomous cars and drones.
  arXiv  Detail & Related papers  (2022-07-26T03:00:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.