So far, running LLMs has required a large amount of computing resources, mainly GPUs. Running locally, a simple prompt with a typical LLM takes on an average Mac ...

Abstract: There are two mainstream approaches for object detection: top-down and bottom-up. The state-of-the-art approaches are mainly top-down methods. In this paper, we demonstrate that bottom-up ...

All common tracking datasets (GOT-10k, OTB, VOT, UAV, TColor, DTB, NfS, LaSOT and TrackingNet) are supported. Support VOT2019 (ST/LT/RGBD/RGBT) downloading. Fix the randomness in ImageNet-VID (issue ...

Abstract: Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy ...