1 code implementation • 15 Dec 2023 • Zhe Ma, Jianfeng Dong, Shouling Ji, Zhenguang Liu, Xuhong Zhang, Zonghui Wang, Sifeng He, Feng Qian, Xiaobo Zhang, Lei Yang
Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval.
no code implementations • 20 Sep 2023 • Chen Jiang, Kaiming Huang, Sifeng He, Xudong Yang, Wei zhang, Xiaobo Zhang, Yuan Cheng, Lei Yang, Qing Wang, Furong Xu, Tan Pan, Wei Chu
SSAN is based on two newly proposed modules in video retrieval: (1) An efficient Self-supervised Keyframe Extraction (SKE) module to reduce redundant frame features, (2) A robust Similarity Pattern Detection (SPD) module for temporal alignment.
1 code implementation • 13 Sep 2023 • Zhenguang Liu, Xinyang Yu, Ruili Wang, Shuai Ye, Zhe Ma, Jianfeng Dong, Sifeng He, Feng Qian, Xiaobo Zhang, Roger Zimmermann, Lei Yang
We theoretically analyzed the mutual information between the label and the disentangled features, arriving at a loss that maximizes the extraction of task-relevant information from the original feature.
1 code implementation • CVPR 2023 • Tan Pan, Furong Xu, Xudong Yang, Sifeng He, Chen Jiang, Qingpei Guo, Feng Qian Xiaobo Zhang, Yuan Cheng, Lei Yang, Wei Chu
For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data.
1 code implementation • 18 Feb 2023 • Feng Qian, Sifeng He, Honghao Huang, Huanyu Ma, Xiaobo Zhang, Lei Yang
With the growing popularity of smartphone photography in recent years, web photos play an increasingly important role in all walks of life.
2 code implementations • 23 Nov 2022 • Sifeng He, Yue He, Minlong Lu, Chen Jiang, Xudong Yang, Feng Qian, Xiaobo Zhang, Lei Yang, Jiandong Zhang
Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints.
1 code implementation • CVPR 2022 • Sifeng He, Xudong Yang, Chen Jiang, Gang Liang, Wei zhang, Tan Pan, Qing Wang, Furong Xu, Chunguang Li, Jingxiong Liu, Hui Xu, Kaiming Huang, Yuan Cheng, Feng Qian, Xiaobo Zhang, Lei Yang
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset.
2 code implementations • 31 Jul 2018 • Sifeng He, Bahram Jalali
A hallucination-free and computationally efficient algorithm for enhancing the resolution of brain MRI images is demonstrated.