No abstract

In order to track all persons in a scene, the tracking-bydetection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.

No abstract

No abstract

PAIR) 2 UT Austin 3 U of Oregon 4 UIUC https://github.com/Picsart-AI-Research/Text2Video-Zero Text-to-Video generation: "a horse galloping on a street" Text-to-Video generation: "a panda is playing guitar on times square" Text-to-Video generation + pose control: "a bear dancing on the concrete" Video Instruct-Pix2Pix: "make it Van Gogh Starry Night style" Text-to-Video generation + edge control: "white butterfly" Figure 1: Our method Text2Video-Zero enables zero-shot video generation using (i) a textual prompt (see rows 1, 2), (ii) a prompt combined with guidance from poses or edges (see lower right), and (iii) Video Instruct-Pix2Pix, i.e., instructionguided video editing (see lower left). Results are temporally consistent and follow closely the guidance and textual prompts.