TA.PB: AI for Image & Video Understanding III |
Session Type: Poster |
Time: Tuesday, September 24, 10:30 - 12:18 |
Location: Room 101 (1F) - Poster Area B |
Session Chair: Antonino Furnari, University of Catania |
TA.PB.1: PARALLEL TEMPORAL ENCODER FOR SIGN LANGUAGE TRANSLATION |
Peipei Song; Hefei University of Technology |
Dan Guo; Hefei University of Technology |
Haoran Xin; Hefei University of Technology |
Meng Wang; Hefei University of Technology |
TA.PB.2: HIGH QUALITY MONOCULAR DEPTH ESTIMATION VIA A MULTI-SCALE NETWORK AND A DETAIL-PRESERVING OBJECTIVE |
Hualie Jiang; Chinese University of Hong Kong, Shenzhen |
Rui Huang; Chinese University of Hong Kong, Shenzhen |
TA.PB.3: A HYBRID L 2 − L P VARIATIONAL MODEL FOR SINGLE LOW-LIGHT IMAGE ENHANCEMENT WITH BRIGHT CHANNEL PRIOR |
Gang Fu; Wuhan University |
Lian Duan; Wuhan University |
Chunxia Xiao; Wuhan University |
TA.PB.4: HELP BY PREDICTING WHAT TO DO |
Edoardo Alati; University of Rome |
Lorenzo Mauro; University of Rome |
Valsamis Ntouskos; University of Rome |
Fiora Pirri; University of Rome |
TA.PB.5: IMPLICIT BACKGROUND ESTIMATION FOR SEMANTIC SEGMENTATION |
Charles Lehman; Georgia Institute of Technology |
Dogancan Temel; Georgia Institute of Technology |
Ghassan AlRegib; Georgia Institute of Technology |
TA.PB.6: LEARNING CHOREOGRAPHIC PRIMITIVES THROUGH A BAYESIAN OPTIMIZED BI-DIRECTIONAL LSTM MODEL |
Ioannis Rallis; National Technical University of Athens |
Nikolaos Bakalos; National Technical University of Athens |
Nikolaos Doulamis; National Technical University of Athens |
Athanasios Voulodimos; University of West Attica |
Anastasios Doulamis; National Technical University of Athens |
Eftychios Protopapadakis; National Technical University of Athens |
TA.PB.7: TEXT RECOGNITION IN IMAGES BASED ON TRANSFORMER WITH HIERARCHICAL ATTENTION |
Yiwei Zhu; Shanghai Jiao Tong University |
Shilin Wang; Shanghai Jiao Tong University |
Zheng Huang; Shanghai Jiao Tong University |
Kai Chen; Shanghai Jiao Tong University |
TA.PB.8: IMPRESSION ESTIMATION FOR DEFORMED PORTRAITS WITH A LANDMARK-BASED RANKING NETWORK |
Mari Miyata; University of Tokyo |
Kiyoharu Aizawa; University of Tokyo |