We present a novel end-to-end transformer-based framework for Multiple Object Tracking (MOT) that advances temporal modeling and identity preservation. Despite recent progress in transformer-based MOT, existing methods still struggle to maintain consistent object identities across frames, especially under occlusions, appearance changes, or detection failures. We propose a dual-path temporal decoder that explicitly separates appearance adaptation and identity preservation. The appearance-adaptive decoder dynamically updates query features using current frame information, while the identity-preserving decoder freezes query features and reuses historical sampling offsets to maintain long-term temporal consistency. To further enhance stability, we introduce a confidence-guided update suppression strategy that retains previously reliable features when predictions are unreliable. Extensive experiments on MOT benchmarks demonstrate that our approach achieves state-of-the-art performance across major tracking metrics, with significant gains in association accuracy and identity consistency. Our results demonstrate the importance of decoupling dynamic appearance modeling from static identity cues, and provide a scalable foundation for robust tracking in complex scenarios.

Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples.

Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.

Manyfew-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity.

Previous works focus their efforts on exploring the support information while paying less attention to the mining of the critical query branch.

In this paper, we focus on utilizing pixel-wise relationships between support and query images to facilitate the few-shot segmentation task.

ACandallReviewers: We thank all reviewers. We discuss the motivation of usingS-based prior later. Asamatter offact,R4alsobrought upthis10 point, yet gave an accept score (7). Imposing15 a prior when available (could come from any source) is application-dependent and can indeed lead to enhanced16 performances, butis,again,notnecessary. Hence, empirical marginals should be closeˆpS(y) ˆpQ(y).

To alleviate this issue, we propose Mask Matching Transformer (MM-Former), a new paradigm for the few-shot segmentation task.