MLSP-P17.9
SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer
Yue Liu, Shanlin Xiao, Bo Li, Zhiyi Yu, Sun Yat-sen University, China
Session:
MLSP-P17: Deep Learning Models III Poster
Track:
Machine Learning for Signal Processing
Location:
Poster Zone 2A
Poster Board PZ-2A.9
Poster Board PZ-2A.9
Presentation Time:
Wed, 17 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Shuai Wang, Shenzhen Research Institute of Big Data &Chinese University of Hong Kong (Shenzhen)
Session MLSP-P17
MLSP-P17.1: SPECTRUMNET: SPECTRUM-BASED TRAJECTORY ENCODE NEURAL NETWORK FOR PEDESTRIAN TRAJECTORY PREDICTION
Shaohua Liu, Yinglong Zhu, Beijing University of Posts and Telecommunications, China; Pengfei Yao, University of Chinese Academy of Sciences, China; Tianlu Mao, Zhaoqi Wang, Institute of Computing Technology Chinese Academy of Sciences, China
MLSP-P17.2: USEE: UNIFIED SPEECH ENHANCEMENT AND EDITING WITH CONDITIONAL DIFFUSION MODELS
Muqiao Yang, Carnegie Mellon University, United States of America; Chunlei Zhang, Yong Xu, Tencent AI Lab, United States of America; Zhongweiyang Xu, University of Illinois Urbana-Champaign, United States of America; Heming Wang, The Ohio State University, United States of America; Bhiksha Raj, Carnegie Mellon University, United States of America; Dong Yu, Tencent AI Lab, United States of America
MLSP-P17.3: ECPNET: AN ENHANCED CURVE PERCEPTION NETWORK FOR LANE DETECTION
Yunzuo Zhang, Yuxin Zheng, Cunyu Wu, Tian Zhang, Yameng Liu, Shijiazhuang Tiedao University, China
MLSP-P17.4: MULTI-STAGE PROGRESSIVE REFINEMENT AND ROI CONTEXT ENHANCEMENT NETWORK FOR SMALL LOGO DETECTION
Songhui Zhao, Sujuan Hou, Shandong Normal University, China
MLSP-P17.5: DBS: Differentiable Budget-aware Searching for channel pruning
Zhaokai Zhang, Tianpeng Feng, Yang Liu, Chunnan Sheng, Fanyi Wang, He Cai, OPPO, China
MLSP-P17.6: CONVERSATION CLIQUE-BASED MODEL FOR EMOTION RECOGNITION IN CONVERSATION
Zhongquan Jian, Jiajian Li, Junfeng Yao, Meihong Wang, Qingqiang Wu, Xiamen University, China
MLSP-P17.7: TITAN: BRINGING THE DEEP IMAGE PRIOR TO IMPLICIT REPRESENTATIONS
Lorenzo Luzi, Rice University, United States of America; Daniel LeJeune, Stanford University, United States of America; Ali Siahkoohi, Sina Alemohammad, Vishwanath Saragadam, Hossein Babaei, Naiming Liu, Zichao Wang, Richard Baraniuk, Rice University, United States of America
MLSP-P17.8: MIXED PRECISION NEURAL QUANTIZATION WITH MULTI-OBJECTIVE BAYESIAN OPTIMIZATION FOR ON-DEVICE DEPLOYMENT
Srinivas S Miriyala, Suhas P K, Utsav Tiwari, Vikram N Rajendiran, Samsung Research Institute, India
MLSP-P17.9: SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer
Yue Liu, Shanlin Xiao, Bo Li, Zhiyi Yu, Sun Yat-sen University, China
MLSP-P17.10: DEFOCUSSR: An EFFICIENT FRAMEWORK FOR DEFOCUS IMAGE SUPER-RESOLUTION GUIDED BY DEPTH INFORMATION
Qirong Liang, Da Pan, Zefeng Ying, Ping Shi, Communication University of China, China
MLSP-P17.11: GMTR: Graph Matching Transformers
Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan, Shanghai Jiaotong University, China
MLSP-P17.12: ADAPTIVE KALMANNET: DATA-DRIVEN KALMAN FILTER WITH FAST ADAPTATION
Xiaoyong Ni, Guy Revach, ETH Zurich, Switzerland; Nir Shlezinger, Ben-Gurion University of the Negev, Beer Sheva, Israe, Israel
Contacts