SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.15096 · CVPR · 2025

When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning

Yang Liu, Qianqian Xu, Qingming Huang, Siran Dai, Peisong Wen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 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.

RepositoryRoleRan
yafeng19/T-CORE — 1 of 1
FunctionStatusWhere it lives
DINOLoss Ran yafeng19/T-CORE/base_model/loss/dino_clstoken_loss.py
code served (permissive licence) · get_code("4abd3fb5be3a56b5")

Repositories linked to this paper

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

Abstract

The past decade has witnessed notable achievements in self-supervised learning for video tasks. Recent efforts typically adopt the Masked Video Modeling (MVM) paradigm, leading to significant progress on multiple video tasks. However, two critical challenges remain: 1) Without human annotations, the random temporal sampling introduces uncertainty, increasing the difficulty of model training. 2) Previous MVM methods primarily recover the masked patches in the pixel space, leading to insufficient information compression for downstream tasks. To address these challenges jointly, we propose a self-supervised framework that leverages Temporal Correspondence for video Representation learning (T-CoRe). For challenge 1), we propose a sandwich sampling strategy that selects two auxiliary frames to reduce reconstruction uncertainty in a two-side-squeezing manner. Addressing challenge 2), we introduce an auxiliary branch into a self-distillation architecture to restore representations in the latent space, generating high-level semantic representations enriched with temporal information. Experiments of T-CoRe consistently present superior performance across several downstream tasks, demonstrating its effectiveness for video representation learning. The code is available at https://github.com/yafeng19/T-CORE.

For agents

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

get_harvested_code_for_paper("2503.15096")
get_code_for_paper("2503.15096")
have("2503.15096")

Connect an agent — have() is free.