Exploring High-Order Self-Similarity for Video Understanding

• URL: http://arxiv.org/abs/2604.20760v1
• Date: Wed, 22 Apr 2026 16:48:43 GMT
• Title: Exploring High-Order Self-Similarity for Video Understanding
• Abstract summary: Multi-Order Self-Similarity (MOSS) is a lightweight neural module designed to learn and integrate multi-order STSS features.<n>It can be applied to diverse video tasks to enhance motion modeling capabilities while consuming only marginal computational cost and memory usage.
• Score: 55.52840327834189
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video understanding. In this work, we explore higher-order STSS and demonstrate how STSSs at different orders reveal distinct aspects of these dynamics. We then introduce the Multi-Order Self-Similarity (MOSS) module, a lightweight neural module designed to learn and integrate multi-order STSS features. It can be applied to diverse video tasks to enhance motion modeling capabilities while consuming only marginal computational cost and memory usage. Extensive experiments on video action recognition, motion-centric video VQA, and real-world robotic tasks consistently demonstrate substantial improvements, validating the broad applicability of MOSS as a general temporal modeling module. The source code and checkpoints will be publicly available.

Related papers

• MVR: Multi-view Video Reward Shaping for Reinforcement Learning [17.20077949643041]
  Multi-View Video Reward Shaping (MVR) is a framework that models the relevance of states regarding the target task using videos captured from multiple viewpoints.<n>MVR learns a state relevance function that mitigates the bias towards specific static poses inherent in image-based methods.<n>We introduce a state-dependent reward shaping formulation that integrates task-specific rewards and VLM-based guidance.
  arXiv  Detail & Related papers  (2026-03-02T10:24:04Z)
• Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders [9.162827706080337]
  We propose a Video-LLM architecture that introduces stacked temporal attention modules directly within the vision encoder.<n>This design incorporates a temporal attention in vision encoder, enabling the model to better capture the progression of actions and the relationships between frames.<n>Our results show that this approach significantly improves temporal reasoning and outperforms existing models in video question answering tasks.
  arXiv  Detail & Related papers  (2025-10-29T23:50:57Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning [54.033346088090674]
  We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability.<n>To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT.<n>This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
  CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning.<n>We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy.<n>We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
  arXiv  Detail & Related papers  (2024-02-08T18:27:22Z)
• MVBench: A Comprehensive Multi-modal Video Understanding Benchmark [63.14000659130736]
  We introduce a comprehensive Multi-modal Video understanding Benchmark, namely MVBench. We first introduce a novel static-to-dynamic method to define these temporal-related tasks. Then, guided by the task definition, we automatically convert public video annotations into multiple-choice QA to evaluate each task.
  arXiv  Detail & Related papers  (2023-11-28T17:59:04Z)
• Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring [82.84513669453744]
  Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs. We revisit temporal modeling in the context of image-to-video knowledge transferring. We present a simple and effective temporal modeling mechanism extending CLIP model to diverse video tasks.
  arXiv  Detail & Related papers  (2023-01-26T14:12:02Z)

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.