AI Paper Atlas

Research map / Video / Video-language understanding

Object Level Visual Reasoning in Videos

Fabien Baradel, Natalia Neverova, Christian Wolf, Julien Mille, Greg Mori

ECCV 2018 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 163 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 object head and ORN module to activity head (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 38.33 -> 40.89Improved
add object head and ORN module to activity head (ablation)Object Relation Network · VLOG ablationmAP (%): 35.03 -> 37.49Improved
add object head and ORN module to activity head (ablation)Object Relation Network · Something-Something ablationtop-1 accuracy (%): 31.31 -> 32.12Improved
use semantically defined COCO objects instead of pixel-level objects (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 38.83 -> 40.89Improved
use semantically defined COCO objects instead of pixel-level objects (ablation)Object Relation Network · VLOG ablationmAP (%): 35.18 -> 37.49Improved
use semantically defined COCO objects instead of pixel-level objects (ablation)Object Relation Network · Something-Something ablationtop-1 accuracy (%): 31.43 -> 32.12Improved
make f_phi recurrent (gated RNN) instead of MLP (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 39.41 -> 40.89Improved
make f_phi recurrent (gated RNN) instead of MLP (ablation)Object Relation Network · VLOG ablationmAP (%): 36.35 -> 37.49Improved
use visual, shape and class features instead of visual only (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 38.92 -> 40.89Improved
use pairwise cliques instead of unary cliques (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 40.18 -> 40.89Improved
use pairwise cliques instead of size-3 cliques (ablation)Object Relation Network · EPIC ablationtop-1 accuracy (%): 37.67 -> 40.89Improved
use 3D kernels instead of 2D kernels (ablation)Object Relation Network · Something-Something valtop-1 accuracy (%): 15.73 -> 31.42Improved

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