{"type":"ScholarlyArticle","title":"MoTRa: Motion-Aware Target Representation Learning for End-to-End Multi-Object Tracking","authors":[{"name":"Yuanzhou Huang","slug":"yuanzhou-huang","given":"Yuanzhou","family":"Huang","affiliation":""},{"name":"Songwei Pei","slug":"songwei-pei","given":"Songwei","family":"Pei","affiliation":""},{"name":"Shuhuai Wang","slug":"shuhuai-wang","given":"Shuhuai","family":"Wang","affiliation":""},{"name":"Bingfeng Liu","slug":"bingfeng-liu","given":"Bingfeng","family":"Liu","affiliation":""},{"name":"Qian Li","slug":"qian-li","given":"Qian","family":"Li","affiliation":""},{"name":"Shangguang Wang","slug":"shangguang-wang","given":"Shangguang","family":"Wang","affiliation":""}],"abstract":"Multi-object tracking (MOT) has long faced challenges with identity switches, especially for targets with low appearance discriminability and complex motion. Existing end-to-end trackers typically enhance robustness by modeling long-term temporal information across target-level representations, yet these representations remain insufficiently discriminative for spatially and visually similar targets. In this paper, we present MoTRa, a Motion-aware Target Representation learning framework for end-to-end MOT that enriches target-level representations with adaptive motion cues. As a result, each representation adaptively balances motion cues and appearance-related content cues under varying conditions, enhancing its discriminability for tracking. To achieve this, we propose a feature fusion and alignment module that extracts motion cues and adaptively fuses them with content features into target representations. To further regularize the dynamically fused representations, we propose a target-specific contrastive learning strategy that promotes intra-trajectory consistency and inter-target separability. Experimental results demonstrate the effectiveness of our method, achieving competitive performance on multiple benchmarks.","doi":"10.24963/ijcai.2026/137","url":"https://ijcai.org/proceedings/2026/137","pdf":"https://ijcai.org/proceedings/2026/0137.pdf","markdown":"https://ijcai.org/proceedings/2026/137.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/137","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":137,"pages":{"first":1224,"last":1232},"keywords":["Computer Vision: Video analysis and understanding","Computer Vision: Motion and tracking","Computer Vision: Representation learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}