Through this repository, we curate a list of papers (and code) for video retrieval, primarily with video as input.
- Self-Supervised Video Representation Learning With Cross-Stream Prototypical Contrasting (WACV) [pdf][code][bibtex]
- Temporal Context Aggregation for Video Retrieval with Contrastive Learning (WACV) [pdf][code][bibtex]
- Towards Explainable Interactive Multi-modal Video Retrieval with Vitrivr (MMM) [pdf][website][bibtex]
- Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval (ICPR) [pdf][bibtex]
- Mixer: Eficiently Understanding and Retrieving Visual Content at Web-scale (VLDB) [pdf][bibtex]
- DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval [ArXiv] [code]
- Video Contrastive Learning with Global Context (ICCV-W) [ArXiv][code]
- Central Similarity Quantization for Efficient Image and Video Retrieval (CVPR) [pdf][code][bibtex]
- Self-supervised Video Representation Learning by Pace Prediction (ECCV) [pdf][code][bibtex]
- Memory-augmented Dense Predictive Coding for Video Representation Learning (ECCV) [pdf][code][bibtex]
- Self-supervised Co-training for Video Representation Learning (NeurIPS) [pdf][code][bibtex]
- ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning (ICCV) [pdf][code][bibtex]
- Video Representation Learning by Dense Predictive Coding (ICCV) [pdf][code][bibtex]
- Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos (ECCV) [pdf][bibtex]
- LAMV: Learning to align and match videos with kernelized temporal layers (CVPR) [pdf][bibtex][code]
Please help contribute this list by creating a pull request with the markdown format:
* <Paper_Title> (<Venue>) [[pdf]](link)[[code]](link)[[bibtex]](link)
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent