Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning

• URL: http://arxiv.org/abs/2606.02321v1
• Date: Mon, 01 Jun 2026 14:35:23 GMT
• Title: Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning
• Abstract summary: In the CVPR 2026 Reason-Aware Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction.<n>We develop Visual Representation-Guided Video-LLM Reasoning for Training-Free Composed Video Retrieval.
• Score: 84.52554180480034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction. To address this task, we develop Visual Representation-Guided Video-LLM Reasoning for Training-Free Composed Video Retrieval. Our framework first uses frozen DINOv3 models to obtain a compact set of visually relevant candidates, and then applies large vision-language models to evaluate whether each candidate satisfies the modification instruction. A final reasoning-based refinement is further performed on the top candidates to improve the first-ranked prediction. Without training, our system achieves 48.78 Recall@1 and 51.48 Recall@5 on the test set. Future work may further improve retrieval accuracy through stronger video-LLMs and detailed integration between visual representations and language reasoning.

Related papers

• ViLL-E: Video LLM Embeddings for Retrieval [55.66444095205989]
  ViLL-E (Video-LLM-Embed) is a unified VideoLLM architecture endowed with a novel embedding generation mechanism.<n>We train this model with a three-stage training methodology combining generative and contrastive learning.<n>Our model significantly improves temporal localization (on avg. 7% over other VideoLLMs) and video retrieval (up to 4% over dual encoder models)
  arXiv  Detail & Related papers  (2026-04-13T23:54:58Z)
• ViSS-R1: Self-Supervised Reinforcement Video Reasoning [84.1180294023835]
  We introduce a novel self-supervised reinforcement learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline.<n>We also propose the ViSS-R1 framework, which streamlines and integrates pretext-task-based self-supervised learning directly into the MLLM's R1 post-training paradigm.
  arXiv  Detail & Related papers  (2025-11-17T07:00:42Z)
• VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding [45.83476222676765]
  We propose Instructed Temporal Grounding for Videos (VideoITG), featuring customized frame sampling aligned with user instructions.<n>The core of VideoITG is the VidThinker pipeline, an automated annotation framework that explicitly mimics the human annotation process.<n>We show that VideoITG achieves consistent performance improvements across multiple multimodal video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-07-17T17:59:59Z)
• Enhancing Subsequent Video Retrieval via Vision-Language Models (VLMs) [3.783822944546971]
  Vision-language models (VLMs) excel in representation learning, but struggle with adaptive, time-sensitive video retrieval.<n>This paper introduces a novel framework that combines vector similarity search with graph-based data structures.
  arXiv  Detail & Related papers  (2025-03-21T01:11:14Z)
• Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection [51.004020874336284]
  VidTFS is a Training-free, open-vocabulary video goal and action inference framework. Our experiments demonstrate that the proposed frame selection module improves the performance of the framework significantly. We validate the performance of the proposed VidTFS on four widely used video datasets.
  arXiv  Detail & Related papers  (2024-01-23T03:45:05Z)
• Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling [79.49128866877922]
  Video-Teller is a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions.
  arXiv  Detail & Related papers  (2023-10-08T03:35:27Z)
• Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought [62.619076257298204]
  We motivate framing video reasoning as the sequential understanding of a small number of video reasonings. We introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in complex video reasoning tasks, and encourage future work.
  arXiv  Detail & Related papers  (2023-05-23T10:26:42Z)

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.