REVIEW 2 cited by
Long-Term Feature Banks for Detailed Video Understanding
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank---supportive information extracted over the entire span of a video---to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.
Forward citations
Cited by 2 Pith papers
-
Fine-Tuning Video Transformers for Word-Level Bangla Sign Language: A Comparative Analysis for Classification Tasks
Off-the-shelf video transformers (VideoMAE, ViViT, TimeSformer) fine-tuned on Bangla sign language videos reach 95.5% top-1 accuracy on BdSLW60 and 81.04% on the BdSLW401 front subset.
-
Three Branches: Detecting Actions With Richer Features
A three-branch fusion of SlowFast global features, person-level RoI features, and long-term feature banks reaches 32.49% mAP on AVA and 21.59% error on Kinetics-700.
Discussion (0). Continue with ORCID to comment.