9 papers
Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration
Xun Jiang, Yufan Gu, Disen Hu +5
Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues…
Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
Bo Zhou, Qiuxia Lai, Zeren Sun +3
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such…
Beyond Quadratic: Linear-Time Change Detection with RWKV
Zhenyu Yang, Gensheng Pei, Tao Chen +4
Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependenci…
OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild
Hongyu Qu, Jianan Wei, Xiangbo Shu +3
Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to i) the scarcity of annotated datasets, and ii) the insufficient diversity of…
Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition
Hongyu Qu, Ling Xing, Jiachao Zhang +3
Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level representations for each video by desi…
Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
Gensheng Pei, Tao Chen, Yujia Wang +4
The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot…
FTMoMamba: Motion Generation with Frequency and Text State Space Models
Chengjian Li, Xiangbo Shu, Qiongjie Cui +2
Diffusion models achieve impressive performance in human motion generation. However, current approaches typically ignore the significance of frequency-domain information in capturi…
UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation
Guangzhao Dai, Jian Zhao, Yuantao Chen +6
Vision-and-Language Navigation (VLN), where an agent follows instructions to reach a target destination, has recently seen significant advancements. In contrast to navigation in di…
AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition
Meiqi Cao, Rui Yan, Xiangbo Shu +3
Panoramic Activity Recognition (PAR) aims to identify multi-granularity behaviors performed by multiple persons in panoramic scenes, including individual activities, group activiti…