AI Paper Atlas

Research map / 3D vision / Human pose estimation

ResQ: Residual Quantization for Video Perception

Davide Abati, Haitam Ben Yahia, Markus Nagel, Amirhossein Habibian

ICCV 2023 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 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
quantize residuals relative to a keyframe at lower precision instead of quantizing each frame independently (ablation)HRNet / DDRNet with PTQ · JHMDB, Cityscapesaccuracy vs BOPs trade-offImproved
add dynamic per-pixel bit-width policy to ResQ (ablation)ResQ · JHMDB pose estimationAvg PCK and GBOPs: 94.3 PCK, 384 GBOPs -> 94.1 PCK, 176 GBOPsImproved
add dynamic bit-width policy on top of static ResQ for STM (ablation)STM VOS · DAVIS-2016J-Mean: 70.2 -> 82.8Improved
use ResQ instead of frame quantization at 4-bit activations for STM (ablation)STM · DAVIS-2016J-Mean: 0.9 -> 70.2Improved
apply QAT instead of PTQ to ResQ (ablation)ResQ DDRNet-23s · CityscapesmIoU: 66.76 -> 77.70Improved
use per-channel instead of per-tensor weight quantization (ablation)ResQ PTQ · CityscapesmIoU: 73.41 -> 75.14; 66.59 -> 66.76Mixed
use pairwise residuals w.r.t. keyframe instead of recurrent frame-to-frame residuals (ablation)ResQ · JHMDB split 1PCKImproved
use a VideoIQ-style learned frame-level precision policy instead of residual-based policy (ablation)Cityscapes segmentation · CityscapesmIoU vs BOPsHurt
apply ResQ with QAT versus the floating point modelDDRNet · CityscapesmIoUImproved
replace 8-bit frame quantization with ResQ at W4A4/W3A3 versus Delta DistillationHRNet-w18s · CityscapesmIoU and BOPs: 75.7 -> 76.9; 2.2 -> 0.9 BOPs (T)Improved
quantize STM to 8 bits with frame quantization (ablation)STM · DAVIS-2016/2017J-Mean: 4.9 and 3.5 drop in J-MeanHurt

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