MLSP-L16.5

MONGOOSE: DO WE NEED A SCANNER FOR VISION MAMBA?

Badri Patro, Vijay Agneeswaran, Microsoft, India
Session:
MLSP-L16: Deep Representation Learning for Signals and Data Oral
Track:
Machine Learning for Signal Processing [ML]
Location:
Room 113
Presentation Time:
Wed, 6 May, 17:50 - 18:10
Presentation
Discussion
Resources
No resources available.
Session MLSP-L16
MLSP-L16.1: SUBTRACTIVE MODULATIVE NETWORK WITH LEARNABLE PERIODIC ACTIVATIONS
Tiou Wang, KTH, Sweden; Zhuoqian Yang, EPFL, Switzerland; Markus Flierl, KTH, Sweden; Mathieu Salzmann, Sabine Süsstrunk, EPFL, Switzerland
MLSP-L16.2: FACESLEUTH-R: ADAPTIVE ORIENTATION-AWARE ATTENTION FOR ROBUST MICRO-EXPRESSION RECOGNITION
LINQUAN WU, City University of Hong, Hong Kong; Tianxiang Jiang, University of Science and Technology of China, China; HAOYU YANG, University of Electronic Science and Technology of China, China; Wenhao Duan, Ocean University of China, China; Shaochao Lin, Harbin Engineering University, China; Zixuan Wang, City University of Hong, Hong Kong; Yini Fang, Hong Kong University of Science and Technology, Hong Kong; Jacky Keung, City University of Hong, Hong Kong
MLSP-L16.3: HFSQVAE: HIERARCHICAL VECTOR QUANTIZATION WITH RESIDUALS FOR FREQUENCY-SPECIFIC EMBEDDING
Min Woo Kim, Seonji Park, Nam Ik Cho, Seoul National University, Korea, Republic of
MLSP-L16.4: D2 -DETR: DUAL-SOURCED AUGMENTATION WITH DURATION-AWARE DIFFERENTIAL DECODER FOR VIDEO TEMPORAL GROUNDING
Peng WANG, Rui MENG, Beijing Normal-Hong Kong Baptist University, China
MLSP-L16.5: MONGOOSE: DO WE NEED A SCANNER FOR VISION MAMBA?
Badri Patro, Vijay Agneeswaran, Microsoft, India
MLSP-L16.6: Vector Quantized Intent Contrastive Learning for Sequential Recommendation
Yuanpeng Qu, Hajime Nobuhara, University of Tsukuba, Japan
Contacts