AI Paper Atlas

Research map / Video / Video-language understanding

Bi-calibration Networks for Weakly-Supervised Video Representation Learning

Fuchen Long, Ting Yao, Zhaofan Qiu, Xinmei Tian, Jiebo Luo, Tao Mei

IJCV 2023 · Video › Video-language understanding · approach: Dense video captioning · 10 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
cluster titles into a text vocabulary and use multi-label classification (TS) instead of regression (RG) (ablation)text supervision · K400 linear, YOVO-3Mtop-1 accuracy (%): 64.5 -> 72.5Improved
use TS instead of triplet ranking (TR) (ablation)text supervision · K400 linear, YOVO-3Mtop-1 accuracy (%): 67.2 -> 72.5Improved
use TS instead of the variant TS- with single-cluster assignment (ablation)text supervision · K400 linear, YOVO-3Mtop-1 accuracy (%): 71.5 -> 72.5Improved
use TS instead of InfoNCE contrastive learning (ablation)video-text learning · K400 lineartop-1 accuracy (%): 72.2 -> 72.5Improved
add text supervision to query supervision (ablation)QS · K400 linear, YOVO-3Mtop-1 accuracy (%): 71.1 -> 73.1Improved
add text-to-query calibration (ablation)QS+TS · K400 linear, YOVO-3Mtop-1 accuracy (%): 73.1 -> 73.8Improved
add query-to-text calibration (ablation)QS+TS · K400 linear, YOVO-3Mtop-1 accuracy (%): 73.1 -> 73.6Improved
use both calibration directions (ablation)QS+TS · K400 linear, YOVO-3Mtop-1 accuracy (%): 73.1 -> 74.2Improved
add bi-calibration on top of QS+TS (ablation)QS+TS · UCF101 linear, YOVO-3Mtop-1 accuracy (%): 92.3 -> 93.5Improved
add bi-calibration on top of QS+TS (ablation)QS+TS · HMDB51 linear, YOVO-3Mtop-1 accuracy (%): 65.9 -> 67.6Improved
pre-train with BCN instead of CPDfine-tuned ResNet-50 · K400 fine-tune, YOVO-3Mtop-1 accuracy (%): 73.9 -> 78.5Improved
scale pre-training data from YOVO-3M to YOVO-10MBCN · K400 fine-tunetop-1 accuracy (%): 78.5 -> 79.1Improved

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