AI Paper Atlas

Research map / Video / Video-language understanding

Neighborhood Preserving Hashing for Scalable Video Retrieval

Shuyan Li, Zhixiang Chen, Jiwen Lu, Xiu Li, Jie Zhou

ICCV 2019 · Video › Video-language understanding · approach: Dense video captioning · 49 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 neighborhood information reconstruction loss (ablation)NPH · FCVID (32 bits)mAP@20: 0.240 -> 0.246Improved
add neighborhood information reconstruction loss (ablation)NPH · FCVID (64 bits)mAP@20: 0.286 -> 0.294Improved
use neighborhood attention instead of anchor concatenation (ablation)NPH · FCVID (32 bits)mAP@20: 0.214 -> 0.240Improved
use neighborhood attention instead of anchor concatenation (ablation)NPH · FCVID (64 bits)mAP@20: 0.254 -> 0.286Improved
replace self-attention with neighborhood attention (visual loss only) (ablation)NPH · FCVID (32 bits)mAP@20: 0.187 -> 0.201Improved
replace self-attention with neighborhood attention (visual loss only) (ablation)NPH · FCVID (64 bits)mAP@20: 0.239 -> 0.238No clear effect
add neighborhood similarity loss to self-attention encoder (ablation)NPH · FCVID (32 bits)mAP@20: 0.187 -> 0.210Improved
add neighborhood similarity loss to self-attention encoder (ablation)NPH · FCVID (64 bits)mAP@100: 0.113 -> 0.162Improved
add neighborhood attention and reconstruction losses on top of SelfAtt+Ls (ablation)NPH · FCVID (32 bits)mAP@20: 0.210 -> 0.240Improved
use fully convolutional encoder instead of LSTM (ablation)FullCNN · FCVID (32 bits)mAP@20: 0.189 -> 0.175No clear effect
NPH versus SSVH on unseen classesNPH · FCVID unseen classesmAP@5: 0.300 -> 0.306Improved
NPH versus SSVH after training on train25NPH · FCVID train25mAP@20: 0.185 -> 0.193Improved

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