Abstract
Multi-modal object tracking (MMOT) has received widespread attention for the ability to overcome single-sensor perception limitations. However, existing methods encounter several critical challenges. Representation learning and generalization capabilities of models are constrained by the inherent heterogeneity of cross-task multi-modal data and inter-modal synergy imbalance. Particularly, in dynamically changing complex scenarios, the reliability and stability of data significantly degrade, further exacerbating the difficulty in multi-modal consistent perception and aggregation. To tackle the above issues, we propose SMUTrack, a unified framework with global shared parameters integrating three downstream MMOT tasks. SMUTrack implements a batch merging-and-splitting alternating strategy, coupled with multi-task joint training, to establish latent correlations across inter- and intra-task modalities, effectively avoiding over-reliance on certain modalities. Concurrently, we design a hierarchical modality synergy and reinforcement (HMSR) module, and a gated fusion and context awareness (GFCA) module to enable progressive multi-modal information exchange and integration, yielding the more discriminative and robust multi-modal representation. More importantly, we introduce a spatial-temporal information propagation (SIP) mechanism, which synchronously learns object trajectory cues and appearance variations to effectively build contextual relationships in long-term video tracking. Experimental results definitively validate the outstanding performance of SMUTrack on mainstream MMOT datasets, exhibiting its powerful adaptability to various MMOT tasks.