AI Paper Atlas

Research map / Video / Video-language understanding

"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval"

Yuxuan Wang, Difei Gao, Licheng Yu, Weixian Lei, Matt Feiszli, Mike Zheng Shou

ECCV 2022 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 25 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 TPD modeling instead of no difference modeling (ablation)ActBERT-revised (ResNet-roi+TSN) · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 67.38 -> 74.71Improved
use TPD modeling instead of simple subtraction (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 67.75 -> 74.71Improved
add simple subtraction difference modeling (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 67.38 -> 67.75No clear effect
add TSN event-granularity feature to ResNet-roi (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 51.93 -> 74.71Improved
add ResNet-roi instant feature to TSN (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 70.80 -> 74.71Improved
add ResNet-conv to ResNet-roi + TSN (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 74.71 -> 65.83Hurt
add ResNet-roi and ResNet-conv to TSN (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 70.80 -> 65.83Hurt
add ResNet-conv to ResNet-roi (ablation)ActBERT-revised · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 51.93 -> 56.64Improved
use one-stream ActBERT-revised instead of two-stream UniVL-revisedTPD, ResNet-roi+TSN · Kinetic-GEB+ Boundary CaptioningCIDEr avg: 65.74 -> 74.71Improved
use FROZEN-revised instead of ActBERT-revisedBoundary Grounding · Kinetic-GEB+ Boundary GroundingF1 avg: 30.66 -> 33.35Improved
use GEBD-based candidate sampling instead of default samplingFROZEN-revised · Kinetic-GEB+ Boundary GroundingF1 avg: 33.35 -> 33.23No clear effect
add difference modeling (ablation)FROZEN-revised · Kinetic-GEB+ Boundary Caption-Video RetrievalmAP: 22.44 -> 23.39Improved

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