Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning

Deng Cai, Fangyun Wei, Minghao Chen, Chong Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• minghchen/carl_code — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Prior works on action representation learning mainly focus on designing various architectures to extract the global representations for short video clips. In contrast, many practical applications such as video alignment have strong demand for learning dense representations for long videos. In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a selfsupervised manner. Concretely, we introduce a simple yet efficient video encoder that considers spatio-temporal context to extract frame-wise representations. Inspired by the recent progress of self-supervised learning, we present a novel sequence contrastive loss (SCL) applied on two correlated views obtained through a series of spatio-temporal data augmentations. SCL optimizes the embedding space by minimizing the KL-divergence between the sequence similarity of two augmented views and a prior Gaussian distribution of timestamp distance. Experiments on FineGym, PennAction and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification. Surprisingly, although without training on paired videos, our approach also shows outstanding performance on video alignment and fine-grained frame retrieval tasks. Code and models are available at https://github.com/ minghchen/CARL_code.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.14957")
get_code_for_paper("2203.14957")
have("2203.14957")

Connect an agent — have() is free.