Related papers: SG-MIM: Structured Knowledge Guided Efficient Pre-…
Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existing approaches lack effective learning of vehicle-related…
Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and…
In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly…
How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…
Foundation models have recently gained tremendous popularity in medical image analysis. State-of-the-art methods leverage either paired image-text data via vision-language pre-training or unpaired image data via self-supervised pre-training…
Deep neural networks have achieved remarkable success in computer vision; however, their black-box nature in decision-making limits interpretability and trust, particularly in safety-critical applications. Interpretability is crucial in…
The computer-assisted radiologic informative report has received increasing research attention to facilitate diagnosis and treatment planning for dental care providers. However, manual interpretation of dental images is limited, expensive,…
Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can…
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this…
Time series imputation models have traditionally been developed using complete datasets with artificial masking patterns to simulate missing values. However, in real-world infrastructure monitoring, practitioners often encounter datasets…
Statistical shape modeling (SSM) characterizes anatomical variations in a population of shapes generated from medical images. SSM requires consistent shape representation across samples in shape cohort. Establishing this representation…
Dense geometric matching determines the dense pixel-wise correspondence between a source and support image corresponding to the same 3D structure. Prior works employ an encoder of transformer blocks to correlate the two-frame features.…
Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…
The landscape of skeleton-based action representation learning has evolved from Contrastive Learning (CL) to Masked Auto-Encoder (MAE) architectures. However, each paradigm faces inherent limitations: CL often overlooks fine-grained local…
The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the…
In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…
We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel RealSense. Traditional structured light methods typically…
Masked Image Modeling (MIM) has achieved impressive representative performance with the aim of reconstructing randomly masked images. Despite the empirical success, most previous works have neglected the important fact that it is…
Due to the scarcity of labeled data, self-supervised learning (SSL) has gained much attention in 3D medical image segmentation, by extracting semantic representations from unlabeled data. Among SSL strategies, Masked image modeling (MIM)…
Magnetic Resonance Imaging (MRI) scans are time consuming and precarious, since the patients remain still in a confined space for extended periods of time. To reduce scanning time, some experts have experimented with undersampled k spaces,…