AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification

Dripta S. Raychaudhuri, Amit K. Roy-Chowdhury

ECCV 2020 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 15 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 the inter-sequence loss to intra-sequence-only TCPL (ablation)TCPL · MARS (one-shot, p=0.05)Rank-1: 63.3 -> 65.2Improved
add the intra-sequence loss to inter-sequence-only TCPL (ablation)TCPL · DukeMTMC-VideoReID (one-shot, p=0.05)Rank-1: 74.4 -> 76.8Improved
add the inter-sequence loss to intra-sequence-only TCPL (ablation)TCPL · DukeMTMC-VideoReID (one-shot, p=0.05)mAP: 67.7 -> 67.9Improved
add temporal consistency losses to progressive pseudo-labeling (TCPL vs One-Shot Prog.)One-Shot Prog. · DukeMTMC-VideoReID (one-shot, p=0.05)Rank-1: 72.9 -> 76.8Improved
add temporal consistency losses to progressive pseudo-labeling (TCPL vs One-Shot Prog.)One-Shot Prog. · MARS (one-shot, p=0.05)Rank-1: 62.8 -> 65.2Improved
use aggressive enlarging factor p=0.20 instead of 0.05 with intra-sequence loss only (ablation)TCPL with L_intra only · DukeMTMC-VideoReID (one-shot)Rank-1: 76.2 -> 74.4Hurt
use aggressive enlarging factor p=0.20 instead of 0.05 for EUG baseline (ablation)EUG · DukeMTMC-VideoReID (one-shot)Rank-1: 72.8 -> 68.9Hurt
add temporal consistency losses at p=0.20 (TCPL L_intra vs One-Shot Prog.)One-Shot Prog. · DukeMTMC-VideoReID (one-shot, p=0.20)Rank-1: 69.1 -> 74.4Improved
raise inter-loss negative rank range r from 2 to 3 (ablation)TCPL with L_inter only · MARS (p=0.20)Rank-1: 53.6 -> 50.8Hurt
lower inter-loss negative rank range r from 2 to 1 (ablation)TCPL with L_inter only · MARS (p=0.20)Rank-1: 53.6 -> 53.1Hurt
increase labeled data from 10% to 20% (few-example)TCPL · MARS (few-example)Rank-1: 72.0 -> 78.2Improved
change random selection of the initial labeled tracklets (ablation)TCPL · DukeMTMC-VideoReID (p=0.20)Rank-1: 74.7 -> 74.4No clear effect

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