TU2.PB: Image and Video Analysis, Synthesis, and Retrieval 7
Tue, 16 Sep, 10:00 - 11:30 Anchorage Time (UTC -8)
Location: Poster Area B
Session Type: Poster
Session Chair: Nicola Conci, University of Trento
Track: [IV-ANA] Image and video analysis, synthesis, and retrieval
Click the to view the manuscript on IEEE Xplore Open Preview

TU2.PB.1: Cwc-DNeRF: Compact Dynamic Neural Radiance Field via Discrete Wavelet Transform and Learnable Codebooks
Yaojian Xu, Shenzhen University, China; Rui Li, Pengcheng Laboratory, China; Qiudan Zhang, Shenzhen University, China; Longhao Zou, Pengcheng Laboratory, China; Qiong Liu, Huazhong University of Science and Technology, China; Xu Wang, Shenzhen University, China

TU2.PB.2: DSFACE : CONDITIONAL DIFFUSION INPAINTING FOR SKETCH-TO-FACE SYNTHESIS
Sanhita Pathak, IIT DELHI, India; Vinay Kaushik, IIIT SONEPAT, India; Brejesh Lall, IIT DELHI, India

TU2.PB.3: FC-RENDER: ADAPTIVE FONT- AND COLOR-AWARE TEXT DIFFUSION MODEL
Bin Chen, Hao Wang, Xilin Zhang, Pinpin Zhu, Shanghai University, China

TU2.PB.4: IN2OUT: FINE-TUNING VIDEO INPAINTING MODEL FOR VIDEO OUTPAINTING USING HIERARCHICAL DISCRIMINATOR
Sangwoo Youn, KAIST, Korea (South); Minji Lee, Columbia University, United States; Nokap Tony Park, Yeonggyoo Jeon, Taeyoung Na, SK Telecom, Korea (South)

TU2.PB.5: Bidirectional Flow Fields for Sparse Input Novel View Synthesis of Dynamic Scenes
Kapil Choudhary, Nagabhushan Somraj, Rajiv Soundararajan, Indian Institute of Science, Bengaluru, India

TU2.PB.6: BOOSTING TEXT-TO-IMAGE PERSON RE-IDENTIFICATION WITH GENERATIVE HARD NEGATIVE
Wei Yue, Hua Yang, Renjie Pan, Shanghai Jiao Tong University, China

TU2.PB.7: AUTOREGRESSION-FREE VIDEO PREDICTION USING DIFFUSION MODEL FOR MITIGATING ERROR PROPAGATION
Woonho Ko, Jin Bok Park, Il Yong Chun, Sungkyunkwan University, Korea (South)

TU2.PB.8: NOISY LABEL REFINEMENT WITH SEMANTICALLY RELIABLE SYNTHETIC IMAGES
Yingxuan Li, The University of Tokyo, Japan; Jiafeng Mao, CyberAgent, Inc., Japan; Yusuke Matsui, The University of Tokyo, Japan

TU2.PB.9: DLP-YOLOV9: MODEL WITH FEWER PARAMETERS AND HIGHER PRECISION BASED ON IMPROVED YOLOV9 IN DRONE-CAPTURED-SCENARIOS
Jian Wang, Jia Su, Capital Normal University, China; Yongqing Sun, Nihon University, Japan

TU2.PB.10: Mirror Feature-Aware Generative Adversarial Network for RGB-T Salient Object Detection
Haoyu Wang, Fangkai Zhao, Fangmei Chen, Fasheng Wang, Fuming Sun, Dalian Minzu University, China

TU2.PB.11: RAPID OBJECT MODELING INITIALIZATION FOR VECTOR QUANTIZED-VARIATIONAL AUTOENCODER
Michael Karnes, Alper Yilmaz, The Ohio State University, United States

TU2.PB.12: BreathAI: Transfer Learning-Based Thermal Imaging for Automated Breathing Pattern Recognition
Hamza Kheddar, University of Medea, Medea, Algeria; Yassine Himeur, University of Dubai, United Arab Emirates; Abbes Amira, University of Sharjah, United Arab Emirates