Deep learning has achieved great success in learning features from massive remote
sensing images (RSIs). To better understand the connection between three feature learning …

To design fast neural networks, many works have been focusing on reducing the number of
floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does …

Driven by improved architectures and better representation learning frameworks, the field of
visual recognition has enjoyed rapid modernization and performance boost in the early …

Tracking often uses a multi-stage pipeline of feature extraction, target information
integration, and bounding box estimation. To simplify this pipeline and unify the process of …

Abstract Contrastive Vision-Language Pre-training, known as CLIP, has provided a new
paradigm for learning visual representations using large-scale image-text pairs. It shows …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

Pre-training by numerous image data has become de-facto for robust 2D representations. In
contrast, due to the expensive data processing, a paucity of 3D datasets severely hinders …

Abstract Video Foundation Models (VFMs) have received limited exploration due to high
computational costs and data scarcity. Previous VFMs rely on Image Foundation Models …

Large, pretrained models are commonly finetuned with imagery that is heavily augmented to
mimic different conditions and scales, with the resulting models used for various tasks with …

FlowFormer introduces a transformer architecture into optical flow estimation and achieves
state-of-the-art performance. The core component of FlowFormer is the transformer-based …