Search Results - "Jin, Weike"

Graph-Based Multi-Interaction Network for Video Question Answering by Gu, Mao, Zhao, Zhou, Jin, Weike, Hong, Richang, Wu, Fei

“…Video question answering is an important task combining both Natural Language Processing and Computer Vision, which requires a machine to obtain a thorough…”
Get full text

Adaptive Spatio-Temporal Graph Enhanced Vision-Language Representation for Video QA by Jin, Weike, Zhao, Zhou, Cao, Xiaochun, Zhu, Jieming, He, Xiuqiang, Zhuang, Yueting

“…Vision-language research has become very popular, which focuses on understanding of visual contents, language semantics and relationships between them. Video…”
Get full text

Video Dialog via Multi-Grained Convolutional Self-Attention Context Multi-Modal Networks by Gu, Mao, Zhao, Zhou, Jin, Weike, Cai, Deng, Wu, Fei

“…Video dialog is a new and challenging task, which requires an AI agent to maintain a meaningful dialog with humans in natural language about video contents…”
Get full text

TaoHighlight: Commodity-Aware Multi-Modal Video Highlight Detection in E-Commerce by Guo, Zhaoyu, Zhao, Zhou, Jin, Weike, Wang, Dazhou, Liu, Ruitao, Yu, Jun

“…In e-commerce, product related video is important content to introduce product characteristics and attract consumers. Especially in the recommendation system…”
Get full text

MLSLT: Towards Multilingual Sign Language Translation by Yin, Aoxiong, Zhao, Zhou, Jin, Weike, Zhang, Meng, Zeng, Xingshan, He, Xiaofei

“…Most of the research to date focuses on bilingual sign language translation (BSLT). However, such models are in-efficient in building multilingual sign…”
Get full text

Multi-Turn Video Question Generation via Reinforced Multi-Choice Attention Network by Guo, Zhaoyu, Zhao, Zhou, Jin, Weike, Wei, Zhicheng, Yang, Min, Wang, Nannan, Yuan, Nicholas Jing

“…Video question generation is a challenging task in visual information retrieval, which generates questions given a sequence of video frames. The existing…”
Get full text

Gloss Attention for Gloss-free Sign Language Translation by Yin, Aoxiong, Zhong, Tianyun, Tang, Li, Jin, Weike, Jin, Tao, Zhao, Zhou

“…Most sign language translation (SLT) methods to date require the use of gloss annotations to provide additional supervision information, however, the…”
Get full text

Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering by Wang, Jiong, Zhao, Zhou, Jin, Weike

“…Multi-modal video question answering aims to predict correct answer and localize the temporal boundary relevant to the question. The temporal annotations of…”
Get full text

Gloss Attention for Gloss-free Sign Language Translation by Yin, Aoxiong, Zhong, Tianyun, Tang, Li, Jin, Weike, Jin, Tao, Zhao, Zhou

“…Most sign language translation (SLT) methods to date require the use of gloss annotations to provide additional supervision information, however, the…”
Get full text

VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation by Wang, Jiong, Zhao, Zhou, Jin, Weike, Duan, Xinyu, Lei, Zhen, Huai, Baoxing, Wu, Yiling, He, Xiaofei

“…For face presentation attack detection (PAD), most of the spoofing cues are subtle, local image patterns (e.g., local image distortion, 3D mask edge and cut…”
Get full text

SimulSLT: End-to-End Simultaneous Sign Language Translation by Yin, Aoxiong, Zhao, Zhou, Liu, Jinglin, Jin, Weike, Zhang, Meng, Zeng, Xingshan, He, Xiaofei

“…Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years. However, the…”
Get full text

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions by Chen, Kai, Gou, Yunhao, Huang, Runhui, Liu, Zhili, Tan, Daxin, Xu, Jing, Wang, Chunwei, Zhu, Yi, Zeng, Yihan, Yang, Kuo, Wang, Dingdong, Xiang, Kun, Li, Haoyuan, Bai, Haoli, Han, Jianhua, Li, Xiaohui, Jin, Weike, Xie, Nian, Zhang, Yu, Kwok, James T, Zhao, Hengshuang, Liang, Xiaodan, Yeung, Dit-Yan, Chen, Xiao, Li, Zhenguo, Zhang, Wei, Liu, Qun, Yao, Jun, Hong, Lanqing, Hou, Lu, Xu, Hang

“…GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However,…”
Get full text