Papers › Holistic Features are almost Sufficient for Text-to-Video Retrieval
Holistic Features are almost Sufficient for Text-to-Video Retrieval
Kaibin Tian, Ruixiang Zhao, Zijie Xin, Bangxiang Lan, Xirong Li
For text-to-video retrieval (T2VR) which aims to retrieve unlabeled videos by ad-hoc textual queries CLIP-based methods currently lead the way. Compared to CLIP4Clip which is efficient and compact state-of-the-art models tend to compute video-text similarity through fine-grained cross-modal feature interaction and matching putting their scalability for large-scale T2VR applications into doubt. We propose TeachCLIP enabling a CLIP4Clip based student network to learn from more advanced yet computationally intensive models. In order to create a learning channel to convey fine-grained cross-modal knowledge from a heavy model to the student we add to CLIP4Clip a simple Attentional frame-Feature Aggregation (AFA) block which by design adds no extra storage / computation overhead at the retrieval stage. Frame-text relevance scores calculated by the teacher network are used as soft labels to supervise the attentive weights produced by AFA. Extensive experiments on multiple public datasets justify the viability of the proposed method. TeachCLIP has the same efficiency and compactness as CLIP4Clip yet has near-SOTA effectiveness.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Retrieval | MSR-VTT-1kA | TeachCLIP (ViT-B/16) | text-to-video R@1 | 48.0 | #27 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | TeachCLIP (ViT-B/16) | text-to-video R@10 | 83.5 | #27 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | TeachCLIP (ViT-B/16) | text-to-video R@5 | 75.9 | #27 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | TeachCLIP | text-to-video R@1 | 46.8 | #31 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | TeachCLIP | text-to-video R@10 | 82.6 | #31 of 63 | Archive leaderboard | report |
| Video Retrieval | MSR-VTT-1kA | TeachCLIP | text-to-video R@5 | 74.3 | #31 of 63 | Archive leaderboard | report |
| Video Retrieval | VATEX | TeachCLIP | text-to-video R@1 | 63.6 | #9 of 13 | Archive leaderboard | report |
| Video Retrieval | VATEX | TeachCLIP | text-to-video R@10 | 96.1 | #9 of 13 | Archive leaderboard | report |
| Video Retrieval | VATEX | TeachCLIP | text-to-video R@5 | 91.9 | #9 of 13 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections