TP2.PC.10
DETECTION TRANSFORMER WITH DIVERSIFIED OBJECT QUERIES
Tharsan Senthivel, ETIS/PMU, France; Ngoc-Son Vu, Boris Borzic, ETIS, France
Session:
TP2.PC: Image and Video Interpretation and Understanding I Poster
Track:
Image and Video Analysis, Synthesis, and Retrieval
Location:
Poster Area C
Presentation Time:
Tue, 10 Oct, 16:30 - 18:00 Malaysia Time (UTC +8)
Session Chair:
Lucas Thomaz, Instituto de Telecomunicações/Polytecnic of Leiria, Portugal
Session TP2.PC
TP2.PC.1: DATASET-LEVEL DIRECTED IMAGE TRANSLATION FOR CROSS-DOMAIN CROWD COUNTING
Xin Tan, Hiroshi Ishikawa, Waseda University, Japan
TP2.PC.2: Adopting Self-supervised Learning into Unsupervised Video Summarization through Restorative score.
Mehryar Abbasi Boroujeni, Parvaneh Saeedi, Simon Fraser University, Canada
TP2.PC.3: Query by Activity Video in the Wild
Tao Hu, University of Amsterdam, Netherlands; William Thong, Sony AI, Switzerland; Pascal Mettes, Cees Snoek, University of Amsterdam, Netherlands
TP2.PC.4: DEEP UNSUPERVISED HASHING WITH SEMANTIC CONSISTENCY LEARNING
Chuang Zhao, Shijie Lu, Hefei Ling, Yuxuan Shi, Bo Gu, Ping Li, Qiang Cao, Huazhong University of Science and Technology, China
TP2.PC.5: Query-based Video Summarization with Pseudo Label Supervision
Jia-Hong Huang, University of Amsterdam, Netherlands; Luka Murn, British Broadcasting Corporation, United Kingdom of Great Britain and Northern Ireland; Marta Mrak, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Marcel Worring, University of Amsterdam, Netherlands
TP2.PC.6: SDAT-FORMER: FOGGY SCENE SEMANTIC SEGMENTATION VIA A STRONG DOMAIN ADAPTATION TEACHER
Ziquan Wang, Yongsheng Zhang, Ying Yu, Zhipeng Jiang, People's Liberation Army Strategic Support Force Information Engineering University, China
TP2.PC.7: Capsule Transformer Network for Dynamic Hand Gesture Recognition using Multimodal Data
Alexandre Lebas, IMT Nord Europe, France; Rim Slama, CESI LINEACT, France; Hazem Wannous, IMT Nord Europe, France
TP2.PC.8: HDTC: Hybrid Model OF DUAL-TRANSFORMER AND CONVOLUTIONAL NEURAL NETWORK FROM RGB-D FOR DETECTION OF LETTUCE GROWTH TRAITS
Zhengxian Wu, Xingpeng Liu, Yiming Xue, Juan Wen, China Agricultural University, China; Wanli Peng, Fudan University, China
TP2.PC.9: Context-Aware Multi-Stream Networks for Dimensional Emotion Prediction in Images
Sidharrth Nagappan, Jia Qi Tan, Lai-Kuan Wong, Multimedia University, Malaysia; John See, Heriot-Watt University, Malaysia
TP2.PC.10: DETECTION TRANSFORMER WITH DIVERSIFIED OBJECT QUERIES
Tharsan Senthivel, ETIS/PMU, France; Ngoc-Son Vu, Boris Borzic, ETIS, France
TP2.PC.11: HANDS IN FOCUS: SIGN LANGUAGE RECOGNITION VIA TOP-DOWN ATTENTION
Noha Sarhan, Christian Wilms, Universität Hamburg, Germany; Vanessa Closius, Ulf Brefeld, Universität Lüneburg, Germany; Simone Frintrop, Universität Hamburg, Germany
TP2.PC.12: PROMPT PROTOTYPE LEARNING BASED ON RANKING INSTRUCTION FOR FEW-SHOT VISUAL TASKS
Li Sun, Liuan Wang, Jun Sun, Fujitsu R&D Center, Beijing, China; Takayuki Okatani, Tohoku University, China
TP2.PC.13: MULTI-EXIT VISION TRANSFORMER WITH CUSTOM FINE-TUNING FOR FINE-GRAINED IMAGE RECOGNITION
Tianyi Shen, Chonghan Lee, Vijaykrishnan Narayanan, Pennsylvania State University, United States of America
Contacts