Pith. sign in

REVIEW 3 cited by

Revisiting 3D ResNets for Video Recognition

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2109.01696 v1 pith:YPA2LSTG submitted 2021-09-03 cs.CV cs.LGeess.IV

Xianzhi Du , Yeqing Li , Yin Cui , Rui Qian , Jing Li , Irwan Bello This is my paper
classification cs.CVcs.LGeess.IV
keywords scalingmodelsrecognitionstrategiestrainingvideoimprovedkinetics-400
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video recognition models. We propose a simple scaling strategy for 3D ResNets, in combination with improved training strategies and minor architectural changes. The resulting models, termed 3D ResNet-RS, attain competitive performance of 81.0 on Kinetics-400 and 83.8 on Kinetics-600 without pre-training. When pre-trained on a large Web Video Text dataset, our best model achieves 83.5 and 84.3 on Kinetics-400 and Kinetics-600. The proposed scaling rule is further evaluated in a self-supervised setup using contrastive learning, demonstrating improved performance. Code is available at: https://github.com/tensorflow/models/tree/master/official.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    CVA aggregates frozen VFM embeddings via latent reasoning to create compact video embeddings for efficient micro-video recommendation, delivering consistent performance gains and orders-of-magnitude efficiency improvements.

  2. Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

    cs.LG 2026-05 conditional novelty 5.0 of 10

    A self-attention-only aggregator over frozen visual embeddings, optionally guided by CLIP-title frame selection, improves short-video recommendation accuracy while cutting training cost.

  3. Few-Shot Learning in Video and 3D Object Detection: A Survey

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A survey of few-shot learning for video and 3D object detection that reviews architectures, losses, and training strategies, but contains numerous citation errors and unsupported performance claims.

Pith tools