AI Paper Atlas

Research map / Video / Video segmentation and tracking

ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors

Xiaoxuan Ma, Stephan Paul Kaufhold, Jiajun Su, Wentao Zhu, Jack Terwilliger, Andres Meza, Yixin Zhu, Federico Rossano, Yizhou Wang

NeurIPS 2023 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 6 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 context (RoI + global pooled feature) to SlowOnly, 8x8x1 (ablation)SlowOnly · ChimpACT action detectionmAP: 20.9 -> 22.3Improved
add context (RoI + global pooled feature) to SlowFast, 8x8x1 (ablation)SlowFast · ChimpACT action detectionmAP: 21.9 -> 24.3Improved
add context to SlowFast, 4x16x1 (ablation)SlowFast · ChimpACT action detectionmAP: 22.0 -> 24.1Improved
change frame sampling from 8x8x1 to 4x16x1 for ACRN (ablation)ACRN · ChimpACT action detectionmAP: 24.4 -> 23.9No clear effect
use Max LFB instead of NL or Avg LFB (ablation)LFB · ChimpACT action detectionmAP: 21.3 -> 23.2Improved
YOLOX detector instead of Faster R-CNN for ByteTrackByteTrack · ChimpACT trackingHOTA: 43.7 -> 49.2Improved
YOLOX detector instead of Faster R-CNN for SORTSORT · ChimpACT trackingHOTA: 42.6 -> 39.8Hurt
YOLOX detector instead of Faster R-CNN for DeepSORTDeepSORT · ChimpACT trackingHOTA: 47.6 -> 40.2Hurt
YOLOX detector instead of Faster R-CNN for OC-SORTOC-SORT · ChimpACT trackingHOTA: 43.4 -> 47.9Improved
add ReID network to SORT (DeepSORT) with Faster R-CNNSORT · ChimpACT trackingIDF1: 42.7 -> 52.8Improved
heatmap-based DarkPose HRNet-W32 vs regression RLE ResNet-152DarkPose · ChimpACT pose estimationAP: 18.1 -> 25.7Improved
deeper backbone ResNet-50 to ResNet-152 for SimpleBaseline (heatmap)SimpleBaseline · ChimpACT pose estimationAP: 22.1 -> 22.7Improved

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