no code implementations • 6 Jun 2023 • Xiaoying Xie, Biao Gong, Yiliang Lv, Zhen Han, Guoshuai Zhao, Xueming Qian
Most recent works focus on answering first order logical queries to explore the knowledge graph reasoning via multi-hop logic predictions.
1 code implementation • 27 Mar 2023 • Siteng Huang, Biao Gong, Yutong Feng, Min Zhang, Yiliang Lv, Donglin Wang
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs.
1 code implementation • ICCV 2023 • Yulin Pan, Xiangteng He, Biao Gong, Yiliang Lv, Yujun Shen, Yuxin Peng, Deli Zhao
Video temporal grounding aims to pinpoint a video segment that matches the query description.
no code implementations • ICCV 2023 • Yutong Feng, Biao Gong, Jianwen Jiang, Yiliang Lv, Yujun Shen, Deli Zhao, Jingren Zhou
ViM consists of a zoo of lightweight plug-in modules, each of which is independently learned on a midstream dataset with a shared frozen backbone.
no code implementations • 1 Mar 2023 • Zeyinzi Jiang, Chaojie Mao, Ziyuan Huang, Yiliang Lv, Deli Zhao, Jingren Zhou
The U-Tuning framework can simultaneously encompass existing methods and derive new approaches for parameter-efficient transfer learning, which prove to achieve on-par or better performances on CIFAR-100 and FGVC datasets when compared with existing PETL methods.
no code implementations • 14 Feb 2023 • Biao Gong, Xiaoying Xie, Yutong Feng, Yiliang Lv, Yujun Shen, Deli Zhao
This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data.
1 code implementation • CVPR 2023 • Siteng Huang, Biao Gong, Yulin Pan, Jianwen Jiang, Yiliang Lv, Yuyuan Li, Donglin Wang
Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models.
1 code implementation • 24 Jul 2022 • Zhiwu Qing, Shiwei Zhang, Ziyuan Huang, Xiang Wang, Yuehuan Wang, Yiliang Lv, Changxin Gao, Nong Sang
Inspired by this, we propose propose Masked Action Recognition (MAR), which reduces the redundant computation by discarding a proportion of patches and operating only on a part of the videos.
Ranked #12 on Action Recognition on Something-Something V2
no code implementations • 4 Aug 2021 • Zhen Han, Xiangteng He, Mingqian Tang, Yiliang Lv
To address the above issues, we propose the Video Similarity and Alignment Learning (VSAL) approach, which jointly models spatial similarity, temporal similarity and partial alignment.
1 code implementation • 26 Jul 2021 • Peng Wu, Xiangteng He, Mingqian Tang, Yiliang Lv, Jing Liu
Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text.
no code implementations • 16 Apr 2021 • Xiangteng He, Yulin Pan, Mingqian Tang, Yiliang Lv
In addition, most retrieval systems are based on frame-level features for video similarity searching, making it expensive both storage wise and search wise.