32 citations · 52 across the 13 of their papers we have counts for
10 papers · 1 filter
AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection
Mohammad Mahdi, Nedyalko Prisadnikov, Yuqian Fu +3
Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning. However, handling diverse vision…
-Scene: Physically Grounded Image-to-3D Scene Reconstruction
Haodong Li, Lulu Shao, Haolin Lu +4
Recent image-to-3D scene methods recover high-fidelity 3D objects with plausible arrangements, but often leave floatings and interpenetrations that limit physical validity and down…
Accelerating Vision Foundation Models with Drop-in Depthwise Convolution
Carmelo Scribano, Mohammad Mahdi, Nedyalko Prisadnikov +5
Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs,…
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Tao Lin, Yuxin Du, Jiting Liu +14
Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often s…
Focusable Monocular Depth Estimation
Yuxin Du, Tao Lin, Zile Zhong +7
Monocular depth foundation models generalize well across scenes, yet they are typically optimized with uniform pixel-wise objectives that do not distinguish user-specified or task-…
Self-supervised pretraining for an iterative image size agnostic vision transformer
Nedyalko Prisadnikov, Danda Pani Paudel, Yuqian Fu +1
Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and sc…
StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
Yifei Wang, Zhenkai Li, Tianwen Qian +4
As embodied intelligence advances toward real-world deployment, the ability to continuously perceive and reason over streaming visual inputs becomes essential. In such settings, an…
ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos
Qi'ao Xu, Tianwen Qian, Yuqian Fu +5
A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG…
MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution
Chengxing Xie, Xiaoming Zhang, Linze Li +4
Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention win…
Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
Yuqian Fu, Yanwei Fu, Yu-Gang Jiang
A recent study finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motiva…