AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection

Kaifeng Gao, Long Chen, Hanwang Zhang, Jun Xiao, Qianru Sun

ICLR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add compositional prompt (separate subject and object contexts) (ablation)RePro relation prompt · VidVRD-test Novel-splitPredCls R@100: 27.43 -> 30.90Improved
add motion-cue-based prompt groups (over compositional only) (ablation)RePro relation prompt · VidVRD-test Novel-splitPredCls R@100: 30.90 -> 33.88Improved
add motion-cue-based prompt groups (over compositional only) (ablation)RePro relation prompt · VidVRD-test All-splitsPredCls mAP: 29.45 -> 34.90Improved
replace motion-based groups with random group selection at train and test (ablation)RePro relation prompt · VidVRD-test Novel-splitSGDet mAP: 7.14 (Rand) vs 6.10 (full)Mixed
ensemble motion prompts by averaging instead of motion-based selection (ablation)RePro relation prompt · VidVRD-test All-splitsSGDet mAP: 20.15 (Ens) vs 21.33 (full)Hurt
add compositional prompt (ablation)RePro relation prompt · VidVRD-test All-splitsSGDet mAP: 19.73 -> 18.47 (compositional without motion)No clear effect
add compositional prompt (ablation)RePro relation prompt · VidOR-val Novel-splitSGCls R@50: 0.86 -> 1.72Improved
add motion-cue prompt groups on top of compositional prompts (ablation)RePro relation prompt · VidOR-val Novel-splitPredCls R@50: 6.62 -> 7.20 (small)No clear effect
full RePro vs fixed-prompt VidVRD-II (re-implemented with ALPro text encoder)relation classification with learned prompts · VidVRD-test Novel-splitSGDet mAP: 3.57 -> 6.10Improved
distill from pretrained visual encoder into V2L projection jointly with prompt learning (RePro†) vs RePro (ablation)relation classification · VidVRD-test Novel-splitSGDet mAP: 2.56 (RePro†) vs 6.10 (RePro)Hurt
add visual distillation (l1 to VLM visual embeddings) to negative-tracklet-loss tracklet detector (ablation)open-vocab tracklet detection · VidOR-valR@10: 12.37 -> 16.85 (with BG-Embd)Improved
replace background embedding with negative-tracklet loss (no BG-Embd) (ablation)open-vocab tracklet detection · VidOR-valR@10: 16.85 -> 37.08Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy