PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

• URL: http://arxiv.org/abs/2412.09613v1
• Date: Thu, 12 Dec 2024 18:59:40 GMT
• Title: PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
• Authors: Chenyu Yang, Xuan Dong, Xizhou Zhu, Weijie Su, Jiahao Wang, Hao Tian, Zhe Chen, Wenhai Wang, Lewei Lu, Jifeng Dai,
• Abstract summary: Visual token compression is leveraged to reduce the considerable token length of visual inputs. We introduce a unified token compression strategy called Progressive Visual Token Compression. Our model achieves state-of-the-art performance across various video understanding benchmarks.
• Score: 64.9366388601049
• License:
• Abstract: Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing high-performance models usually process images and videos separately with different token compression strategies, limiting the capabilities of combining images and videos. To this end, we extend each image into a "static" video and introduce a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames. Video tokens are efficiently compressed with exploiting the inherent temporal redundancy. Images are repeated as static videos, and the spatial details can be gradually supplemented in multiple frames. PVC unifies the token compressing of images and videos. With a limited number of tokens per frame (64 tokens by default), spatial details and temporal changes can still be preserved. Experiments show that our model achieves state-of-the-art performance across various video understanding benchmarks, including long video tasks and fine-grained short video tasks. Meanwhile, our unified token compression strategy incurs no performance loss on image benchmarks, particularly in detail-sensitive tasks.

Related papers

• Large Motion Video Autoencoding with Cross-modal Video VAE [52.13379965800485]
  Video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Existing Video VAEs have begun to address temporal compression; however, they often suffer from inadequate reconstruction performance. We present a novel and powerful video autoencoder capable of high-fidelity video encoding.
  arXiv  Detail & Related papers  (2024-12-23T18:58:24Z)
• DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models [28.379533608574814]
  We present DyCoke, a training-free token compression method to optimize token representation and accelerate video large language models. DyCoke incorporates a plug-and-play temporal compression module to minimize temporal redundancy by merging redundant tokens across frames. It ensures high-quality inference by dynamically retaining the critical tokens at each decoding step.
  arXiv  Detail & Related papers  (2024-11-22T15:55:19Z)
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding [65.46303012350207]
  LongVU is an adaptive compression mechanism that reduces the number of video tokens while preserving visual details of long videos. We leverage DINOv2 features to remove redundant frames that exhibit high similarity. We perform spatial token reduction across frames based on their temporal dependencies.
  arXiv  Detail & Related papers  (2024-10-22T21:21:37Z)
• VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models [25.668485023831874]
  VidCompress is a novel Video-LLM featuring memory-enhanced temporal compression. It efficiently models complex temporal-spatial relations and significantly outperforms existing Video-LLMs.
  arXiv  Detail & Related papers  (2024-10-15T09:07:25Z)
• VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding [15.959757105308238]
  Video LMMs rely on either image or video encoders to process visual inputs, each of which has its own limitations. We introduce VideoGPT+, which combines the complementary benefits of the image encoder (for detailed spatial understanding) and the video encoder (for global temporal context modeling) Our architecture showcases improved performance across multiple video benchmarks, including VCGBench, MVBench and Zero-shot question-answering.
  arXiv  Detail & Related papers  (2024-06-13T17:59:59Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VidToMe: Video Token Merging for Zero-Shot Video Editing [100.79999871424931]
  We propose a novel approach to enhance temporal consistency in generated videos by merging self-attention tokens across frames. Our method improves temporal coherence and reduces memory consumption in self-attention computations.
  arXiv  Detail & Related papers  (2023-12-17T09:05:56Z)
• Accurate and Fast Compressed Video Captioning [28.19362369787383]
  Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process. We study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning.
  arXiv  Detail & Related papers  (2023-09-22T13:43:22Z)
• Compressed Vision for Efficient Video Understanding [83.97689018324732]
  We propose a framework enabling research on hour-long videos with the same hardware that can now process second-long videos. We replace standard video compression, e.g. JPEG, with neural compression and show that we can directly feed compressed videos as inputs to regular video networks.
  arXiv  Detail & Related papers  (2022-10-06T15:35:49Z)
• SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning [40.556222166309524]
  We present SwinBERT, an end-to-end transformer-based model for video captioning. Our method adopts a video transformer to encode spatial-temporal representations that can adapt to variable lengths of video input. Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames.
  arXiv  Detail & Related papers  (2021-11-25T18:02:12Z)

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.