AI Paper Atlas

Research map / Video / Video-language understanding

ResidualViT for Efficient Temporally Dense Video Encoding

Mattia Soldan, Fabian Caba Heilbron, Bernard Ghanem, Josef Sivic, Bryan Russell

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 1 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 interleaving of full-encoded I-frames with token-reduced P-frames (N=2) (ablation)token-reduced CLIP ViT-L/14 · Charades-STA NLTVG ablation (ViT-L/14)R@1 IoU=0.5: 28.5 -> 38.9Improved
add interleaving (N=2) (ablation)token-reduced CLIP ViT-L/14 · Charades-STA NLTVG ablation (ViT-L/14)R@1 IoU=0.7: 14.5 -> 22.8Improved
add distilled residual tokenizer (ablation)ResidualViT (reduction + interleave) · Charades-STA NLTVG ablation (ViT-L/14)R@1 IoU=0.5: 38.9 -> 41.5Improved
add distilled residual tokenizer (ablation)ResidualViT (reduction + interleave) · Charades-STA NLTVG ablation (ViT-L/14)R@1 IoU=0.7: 22.8 -> 23.8Improved
add distilled residual tokenizer (ablation)ResidualViT (reduction + interleave) · Charades-STA NLTVG ablation (ViT-L/14)encoding cost (GFLOPs/sec): 102.0 -> 102.6No clear effect
apply token reduction (85% dropped) to all frames vs full CLIP (ablation)CLIP ViT-L/14 · Charades-STA NLTVG ablation (ViT-L/14)R@1 IoU=0.5: 42.9 -> 28.5Hurt
replace CLIP with ResidualViT (N=2, p=85%)CLIP ViT-L/14 · Charades-STA zero-shot NLTVGR@1 IoU=0.5: 42.9 -> 41.5No clear effect
replace CLIP with ResidualViTCLIP ViT-L/14 · MAD zero-shot NLTVGR@1 IoU=0.5: 5.0 -> 4.3Hurt
replace CLIP with ResidualViTCLIP ViT-L/14 · ActivityNet-v1.3 TAL (ActionFormer)mAP (%): 34.83 -> 34.46No clear effect
replace CLIP with ResidualViTCLIP ViT-L/14 · MAD audio descriptionCIDEr: 11.3 -> 10.6Hurt
replace CLIP with ResidualViTCG-DETR (B/32) · Charades-STA fully supervised CG-DETR (B/32)R@1 IoU=0.5: 49.7 -> 48.2No clear effect
increase interleave factor N beyond 2 (ablation)ResidualViT · Charades-STA NLTVG ablation (ViT-L/14)R@1 accuracyHurt

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