A Clip-hitchhiker's Guide To Long Video Retrieval

Abstract

Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and mean-pooling. In doing so, we provide an improved baseline for others to compare to and demonstrate state-of-the-art performance of this simple baseline on a suite of long video retrieval benchmarks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybain2022a

Related papers

• Prompt Switch: Efficient CLIP Adaptation For Text-video Retrieval (2023)11.93
• HVD: Human Vision-driven Video Representation Learning For Text-video Retrieval (2026)0.00
• An Empirical Study Of Excitation And Aggregation Design Adaptions In Clip4clip For Video-text Retrieval (2024)4.52
• Clip4clip: An Empirical Study Of CLIP For End To End Video Clip Retrieval (2021)6.02
• X-CLIP: End-to-end Multi-grained Contrastive Learning For Video-text Retrieval (2022)18.12
• Towards Efficient And Robust Moment Retrieval System: A Unified Framework For Multi-granularity Models And Temporal Reranking (2025)2.26
• CLIP2TV: Align, Match And Distill For Video-text Retrieval (2021)0.00
• TV-RAG: A Temporal-aware And Semantic Entropy-weighted Framework For Long Video Retrieval And Understanding (2025)2.86