The University of California, Merced (UC Merced), established in 2005, is the newest campus within the University of California system and a public land-grant research university. Located in California’s San Joaquin Valley, it focuses on increasing access to higher education and is committed to sustainability. NECLA collaborated with UC Merced to advance multimodal AI learning by leveraging the synergy between large-scale visual and textual representations. We have enhanced the performance of AI models in real-world applications, such as captioning, object recognition, and low-label environments.

Posts

Fast and Accurate Online Video Object Segmentation via Tracking Parts

/in /by

Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

Read more