no code implementations • 4 Dec 2024 • Qi Zheng, Yibo Fan, Leilei Huang, Tianyu Zhu, Jiaming Liu, Zhijian Hao, Shuo Xing, Chia-Ju Chen, Xiongkuo Min, Alan C. Bovik, Zhengzhong Tu
Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner highly consistent with human judgments of perceived quality.
1 code implementation • 20 Jun 2024 • Yihong Wu, Le Zhang, Fengran Mo, Tianyu Zhu, Weizhi Ma, Jian-Yun Nie
By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity.
1 code implementation • 12 Apr 2024 • Tianyu Zhu, Myong Chol Jung, Jesse Clark
Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal requirement for manual annotations.
1 code implementation • 30 Jan 2024 • Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, Jian-Yun Nie
To address the aforementioned issues, we propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals based on the actual impact of historical turns.
no code implementations • 18 Jan 2024 • Tianyu Zhu, Heming Sun, Xiankui Xiong, Xuanpeng Zhu, Yong Gong, Minge jing, Yibo Fan
Our experiments compare the effects of different dimensions such as attack methods, models, qualities, and targets, concluding that in the worst case, there is a 61. 55% decrease in PSNR or a 19. 15 times increase in bpp under the PGD attack.
1 code implementation • 2 Nov 2023 • Tianyu Zhu, Yansong Shi, Yuan Zhang, Yihong Wu, Fengran Mo, Jian-Yun Nie
Second, we develop a transition-aware embedding distillation module that distills global item-to-item transition patterns into item embeddings, which enables the model to memorize and leverage transitional signals and serves as a calibrator for collaborative signals.
1 code implementation • CVPR 2023 • Tianyu Zhu, Bryce Ferenczi, Pulak Purkait, Tom Drummond, Hamid Rezatofighi, Anton Van Den Hengel
Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations are used instead.
1 code implementation • 7 Dec 2021 • Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tianyu Zhu, Tom Drummond, Mehrtash Harandi
A principle way of achieving few-shot learning is to realize a model that can rapidly adapt to the context of a given task.
no code implementations • 12 Nov 2021 • Tianyu Zhu, Rongkai Ma, Mehrtash Harandi, Tom Drummond
A segmentation model cannot easily learn from prior information given in the visual tracking scenario.
1 code implementation • 27 Mar 2021 • Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Ian Reid, Hamid Rezatofighi
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
no code implementations • 30 Jan 2020 • Hamid Rezatofighi, Tianyu Zhu, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixé, Ian Reid
In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality.