AI Paper Atlas

Research map / Video / Action recognition

Self-Supervised Video Representation Learning With Meta-Contrastive Network

Yuanze Lin, Xun Guo, Yan Lu

ICCV 2021 · Video › Action recognition · approach: Contrastive video representation learning · 43 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 MCN (meta-contrastive training) to the CMC baselineCMC baseline R3D-18 · UCF101 fine-tune (pretrain UCF101)top-1 accuracy (%): 78.6 -> 85.4Improved
add MCN to the CMC baselineCMC baseline S3D · UCF101 fine-tune (pretrain UCF101)top-1 accuracy (%): 76.7 -> 82.9Improved
add MCN to the CMC baselineCMC baseline R3D-18 · HMDB51 fine-tune (pretrain UCF101)top-1 accuracy (%): 47.1 -> 54.8Improved
add MCN to the CMC baselineCMC baseline R3D-18 · UCF101 linear probetop-1 accuracy (%): 64.6 -> 73.1Improved
add MCN to the CMC baselineCMC baseline R3D-18 · HMDB51 linear probetop-1 accuracy (%): 37.3 -> 42.9Improved
set meta loss weight alpha to 0.2 instead of 0.4 (ablation)MCN R(2+1)D · UCF101 fine-tune (alpha sweep)top-1 accuracy (%): 82.7 -> 84.8Improved
set alpha to 0.2 instead of 0.1 (ablation)MCN R(2+1)D · UCF101 fine-tune (alpha sweep)top-1 accuracy (%): 84.1 -> 84.8Improved
increase input frames from 16 to 64 (ablation)MCN R(2+1)D · UCF101 fine-tune (input frames)top-1 accuracy (%): 81.3 -> 86.7Improved
increase input frames from 16 to 64 (ablation)Baseline R(2+1)D · UCF101 fine-tune (input frames)top-1 accuracy (%): 74.6 -> 80.6Improved
add binary classification loss from the meta branch (ablation)CMC baseline R(2+1)D · UCF101 fine-tune (component ablation)top-1 accuracy (%): 77.3 -> 79.2Improved
add meta-train/meta-test stages (ablation)CL + BL R(2+1)D · UCF101 fine-tune (component ablation)top-1 accuracy (%): 79.2 -> 84.8Improved
pre-train on Kinetics-400 instead of UCF101MCN R3D · UCF101 fine-tunetop-1 accuracy (%): 85.4 -> 89.7Improved

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