{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/joint-spatial-temporal-and-appearance","title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","arxiv_id":"2205.15495","date":"2022-05-31","proceeding":null,"authors":["Peng Dai","Yiqiang Feng","Renliang Weng","ChangShui Zhang"],"abstract":"The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between the tracklets and the detections by taking both spatial-temporal and appearance features into account. TransSTAM has two major advantages: (1) It is solely based on the encoder-decoder architecture and enjoys a compact network design, hence being computationally efficient; (2) It can effectively learn spatial-temporal and appearance features within one model, hence achieving better tracking accuracy. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA with respect to previous state-of-the-art approaches on all the benchmarks. Our code is available at \\url{https://github.com/icicle4/TranSTAM}.","url_abs":"https://arxiv.org/abs/2205.15495v1","url_pdf":"https://arxiv.org/pdf/2205.15495v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"joint-spatial-temporal-and-appearance","repo_url":"https://github.com/icicle4/transtam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}