CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attentionby…
Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusionby Yuntao Shou, Tao…
Optimizing Cycle Life Prediction of Lithium-ion Batteries via a Physics-Informed Modelby Constantin-Daniel Nicolae, Sara Sameer,…
Data-independent Module-aware Pruning for Hierarchical Vision Transformersby Yang He, Joey Tianyi ZhouFirst submitted to arxiv…
StrideNET: Swin Transformer for Terrain Recognition with Dynamic Roughness Extractionby Maitreya Shelare, Neha Shigvan, Atharva…
MCM: Multi-condition Motion Synthesis Frameworkby Zeyu Ling, Bo Han, Yongkang Wongkan, Han Lin, Mohan Kankanhalli,…
Transformer-Based Classification Outcome Prediction for Multimodal Stroke Treatmentby Danqing Ma, Meng Wang, Ao Xiang, Zongqing…
LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memoryby Zicheng Liu, Li Wang, Siyuan…
Anomaly Correction of Business Processes Using Transformer Autoencoderby Ziyou Gong, Xianwen Fang, Ping WuFirst submitted…
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Modelsby Guangyan Li, Yongqiang Tang,…