ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search

arXiv:2601.23232 · cs.CV, cs.AI · Submitted 2026-01-30 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-01-30

Updated: 2026-09-16

Comments: EMNLP 2026 Findings, 30 pages, 9 figures, Project website: https://github.com/yutao1024/ShotFinder

Code: https://github.com/yutao1024/ShotFinder

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 27× in this paper · explained in 2 episodes
• Verification — 16× in this paper · explained in 2 episodes
• Grounding — 12× in this paper · explained in 3 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Consistency — 9× in this paper · explained in 3 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Ontology — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
• Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
• WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
• CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
• UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
• SKALD: Learning-Based Shot Assembly for Coherent Multi-Shot Video Creation
• Learning to Cut by Watching Movies
• Learning Transferable Visual Models From Natural Language Supervision
• Playing for Data: Ground Truth from Computer Games
• Chrono: A Simple Blueprint for Representing Time in MLLMs
• WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
• Audio-Visual Event Localization in Unconstrained Videos
• WebDancer: Towards Autonomous Information Seeking Agency
• WebWalker: Benchmarking LLMs in Web Traversal
• Qwen3-Omni Technical Report
• Qwen3 Technical Report
• Aligning Multimodal LLM with Human Preference: A Survey
• BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models