AI Paper Atlas

Research map / Video / Video-language understanding

Inverse Compositional Learning for Weakly-supervised Relation Grounding

Huan Li, Ping Wei, Zeyu Ma, Nanning Zheng

ICCV 2023 · Video › Video-language understanding · approach: Temporal video grounding · 2 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 holistic inverse learning and partial-level learning to the reconstruction baseline (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 24.10 -> 26.05Improved
add predicate term of partial-level classification loss (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 22.68 -> 26.05Improved
add subject term of partial-level classification loss (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 25.06 -> 26.05Improved
add object term of partial-level classification loss (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 25.07 -> 26.05Improved
add L+- inverse learning term (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 24.04 -> 26.05Improved
add L-+ inverse learning term (ablation)ICL · ImageNet-VidVRD (sIoU=0.3)AccR (%): 32.20 -> 31.85 at sIoU=0.3; 17.76 -> 18.46 at sIoU=0.7Mixed
use three-term inverse loss with partly relevant features instead of delta(d++ - d--) only (ablation)ICL · ImageNet-VidVRD (average)AccR (%): 24.49 -> 26.05Improved
add predicate term of partial loss (ablation)ICL · HICO-DET (sIoU=0.5)AccR (%): 36.91 -> 46.09Improved
add object term of partial loss (ablation)ICL · HICO-DET (sIoU=0.5)AccR (%): 24.21 -> 46.09Improved
use inverse loss with three terms instead of single delta term (ablation)ICL · HICO-DET (sIoU=0.5)AccR (%): 22.54 -> 46.09Improved
ICL versus ARC without Viterbi decodingICL · ImageNet-VidVRD (average)AccR (%): 23.75 -> 26.05Improved
ICL versus ARC with Viterbi decodingICL# · ImageNet-VidVRD (average)AccS and AccR (%): AccS 39.66 -> 39.57; AccR 26.42 -> 27.87Mixed

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