# 3D-CSL: self-supervised 3D context similarity learning for Near-Duplicate Video Retrieval

arXiv: https://arxiv.org/abs/2211.05352 · HTML: https://mlsanity.com/paper/2211.05352/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 10 Nov 2022.

## Builds on (most cited first, 15 of 15)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning](https://mlsanity.com/paper/1908.07410/) (2019)
- [Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder](https://mlsanity.com/paper/1802.02305/) (2018)
- [FIVR: Fine-grained Incident Video Retrieval](https://mlsanity.com/paper/1809.04094/) (2018)
- [Visual Chirality](https://mlsanity.com/paper/2006.09512/) (2020)

## Built on by (most cited first, 4 of 4)

- [Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval](https://mlsanity.com/paper/2309.08167/) (2023)
- [Counteracting temporal attacks in Video Copy Detection](https://mlsanity.com/paper/2501.11171/) (2025)
- [Semi-supervised 3D Video Information Retrieval with Deep Neural Network and Bi-directional Dynamic-time Warping Algorithm](https://mlsanity.com/paper/2309.01063/) (2023)
- [Efficient Logic Gate Networks for Video Copy Detection](https://mlsanity.com/paper/2604.21694/) (2026)

## Abstract (arXiv)

In this paper, we introduce 3D-CSL, a compact pipeline for Near-Duplicate Video Retrieval (NDVR), and explore a novel self-supervised learning strategy for video similarity learning. Most previous methods only extract video spatial features from frames separately and then design kinds of complex mechanisms to learn the temporal correlations among frame features. However, parts of spatiotemporal dependencies have already been lost. To address this, our 3D-CSL extracts global spatiotemporal dependencies in videos end-to-end with a 3D transformer and find a good balance between efficiency and effectiveness by matching on clip-level. Furthermore, we propose a two-stage self-supervised similarity learning strategy to optimize the entire network. Firstly, we propose PredMAE to pretrain the 3D transformer with video prediction task; Secondly, ShotMix, a novel video-specific augmentation, and FCS loss, a novel triplet loss, are proposed further promote the similarity learning results. The experiments on FIVR-200K and CC_WEB_VIDEO demonstrate the superiority and reliability of our method, which achieves the state-of-the-art performance on clip-level NDVR.