The Devil is in Temporal Token: High Quality Video Reasoning Segmentation

• URL: http://arxiv.org/abs/2501.08549v1
• Date: Wed, 15 Jan 2025 03:17:24 GMT
• Title: The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
• Authors: Sitong Gong, Yunzhi Zhuge, Lu Zhang, Zongxin Yang, Pingping Zhang, Huchuan Lu,
• Abstract summary: Methods for Video Reasoning rely heavily on a single special token to represent the object in the video. We propose VRS-HQ, an end-to-end video reasoning segmentation approach. Our results highlight the strong temporal reasoning and segmentation capabilities of our method.
• Score: 68.33080352141653
• License:
• Abstract: Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these challenges, we propose VRS-HQ, an end-to-end video reasoning segmentation approach that leverages Multimodal Large Language Models (MLLMs) to inject rich spatiotemporal features into hierarchical tokens.Our key innovations include a Temporal Dynamic Aggregation (TDA) and a Token-driven Keyframe Selection (TKS). Specifically, we design frame-level <SEG> and temporal-level <TAK> tokens that utilize MLLM's autoregressive learning to effectively capture both local and global information. Subsequently, we apply a similarity-based weighted fusion and frame selection strategy, then utilize SAM2 to perform keyframe segmentation and propagation. To enhance keyframe localization accuracy, the TKS filters keyframes based on SAM2's occlusion scores during inference. VRS-HQ achieves state-of-the-art performance on ReVOS, surpassing VISA by 5.9%/12.5%/9.1% in J&F scores across the three subsets. These results highlight the strong temporal reasoning and segmentation capabilities of our method. Code and model weights will be released at VRS-HQ.

Related papers

• VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection [61.54044967253421]
  We introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM.
  arXiv  Detail & Related papers  (2024-11-22T08:33:36Z)
• Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding [11.211803499867639]
  We propose DYTO, a novel dynamic token merging framework for zero-shot video understanding. DYTO integrates a hierarchical frame selection and a bipartite token merging strategy to dynamically cluster key frames and selectively compress token sequences. Experiments demonstrate the effectiveness of DYTO, achieving superior performance compared to both fine-tuned and training-free methods.
  arXiv  Detail & Related papers  (2024-11-21T18:30:11Z)
• Slot-VLM: SlowFast Slots for Video-Language Modeling [39.474247695753725]
  Video-Language Models (VLMs) are powered by the advancements in Large Language Models (LLMs) In this work, we introduce Slot-VLM, a novel framework designed to generate semantically decomposed video tokens. Our experimental results demonstrate the effectiveness of our Slot-VLM, which achieves the state-of-the-art performance on video question-answering.
  arXiv  Detail & Related papers  (2024-02-20T15:30:09Z)
• DVIS++: Improved Decoupled Framework for Universal Video Segmentation [30.703276476607545]
  We present OV-DVIS++, the first open-vocabulary universal video segmentation framework. By integrating CLIP with DVIS++, we present OV-DVIS++, the first open-vocabulary universal video segmentation framework.
  arXiv  Detail & Related papers  (2023-12-20T03:01:33Z)
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding [63.075626670943116]
  We introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer.
  arXiv  Detail & Related papers  (2023-12-04T19:48:02Z)
• Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation [76.68301884987348]
  We propose a simple yet effective approach for self-supervised video object segmentation (VOS) Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust-temporal segmentation correspondences in videos. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and excels in complex real-world multi-object video segmentation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:47:17Z)
• Multi-entity Video Transformers for Fine-Grained Video Representation Learning [36.31020249963468]
  We re-examine the design of transformer architectures for video representation learning. A salient aspect of our self-supervised method is the improved integration of spatial information in the temporal pipeline. Our Multi-entity Video Transformer (MV-Former) architecture achieves state-of-the-art results on multiple fine-grained video benchmarks.
  arXiv  Detail & Related papers  (2023-11-17T21:23:12Z)
• UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization [16.963092523737593]
  We propose a novel framework for temporal forgery localization (TFL) that predicts forgery segments with multimodal adaptation. Our approach achieves state-of-the-art performance on benchmark datasets, including Lav-DF, TVIL, and Psynd.
  arXiv  Detail & Related papers  (2023-08-28T08:20:30Z)
• Video Mask Transfiner for High-Quality Video Instance Segmentation [102.50936366583106]
  Video Mask Transfiner (VMT) is capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure. Based on our VMT architecture, we design an automated annotation refinement approach by iterative training and self-correction. We compare VMT with the most recent state-of-the-art methods on the HQ-YTVIS, as well as the Youtube-VIS, OVIS and BDD100K MOTS.
  arXiv  Detail & Related papers  (2022-07-28T11:13:37Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

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.