The appearance information of the target has been used as the only tracking cue for most trackers to locate the target in the video. However, when the surrounding environment changes drastically or there are similar interference targets, it usually causes target drift. We propose a tracker named MRTrack, a transformer-based spatiotemporal information de coupling network architecture to enhance the target tracking capability. We designed two training schemes to explore the effective integration of motion cues derived from optical flow with representation information. The first approach integrates the target's motion and representation information for training. The second scheme is a step-by-step training, where the target motion information is first learned, and the learned model is used for representation learning. We compare the two training methods on five generic tracking datasets. The experiment results indicate that the first training approach can better integrate motion and representation information, leading to more precise tracking results for MRTrack compared to solely relying on the appearance model. In addition, optical flow cues are used only in the training phase to guide the tracker in understanding motion information, and no additional cost is incurred during tracking inference.

Rapid advancements in large multimodal models (LMMs) have significantly enhanced their applications in pathology, particularly in image classification, pathology image description, and whole slide image (WSI) classification. In pathology, WSIs represent gigapixel-scale images composed of thousands of image patches. Therefore, both patch-level and WSI-level evaluations are essential and inherently interconnected for assessing LMM capabilities. In this work, we propose PathBench, which comprises three subsets at both patch and WSI levels, to refine and enhance the validation of LMMs. At the patch-level, evaluations using existing multi-choice Q&A datasets reveal that some LMMs can predict answers without genuine image analysis. To address this, we introduce PatchVQA, a large-scale visual question answering (VQA) dataset containing 5,382 images and 6,335 multiple-choice questions designed with distractor options to prevent shortcut learning. These new questions are rigorously validated by professional pathologists to ensure reliable model assessments. At the WSI-level, current efforts primarily focus on image classification tasks and lack diverse validation datasets for multimodal models. To address this, we generate a detailed WSI report dataset through an innovative approach that integrates detailed patch descriptions generated by foundational models into comprehensive WSI reports. These are then combined with physician-written reports corresponding to TCGA WSIs, resulting in WSICap, a detailed report dataset containing 7,000 samples. Based on WSICap, we further develop a WSI-level VQA dataset, WSIVQA, to serve as a validation set for WSI LMMs. Using these PathBench subsets, we conduct extensive experiments to benchmark the performance of state-of-the-art LMMs at both the patch and WSI levels. The proposed dataset is available at https://github.com/superjamessyx/PathBench.

The Crater Detection (CD) presents challenges due to complex backgrounds, tiny scales, and dense distribution of small craters. To address these problems, we propose a new DEtection TRansformer (DETR) variant network for crater detection called Crater-DETR. First, we design the Correspond Regional Attention Upsample (CRAU) and Pooling (CRAP) operators through cross-attention computing to address the problem of foreground-background confusion caused by the feature loss of small craters. Then, to address the weak supervision due to the fixed number query selection and to introduce dense supervision, we propose the Dense Auxiliary Head Supervise (DAHS) training. Next, Automatic DeNoising (ADN) training is proposed to solve the problem of sparse positive queries in the Decoder to improve the decoding capability. Finally, we propose a Small Object Stable Intersection over Union (SOSIoU) Loss to optimize the training process since the matching process is more unstable in small craters compared to other sizes of craters. Experimental results show that Crater-DETR achieves a precision of 88.13% on DACD dataset, yielding state-of-the-art performance. Furthermore, our method also achieved the best performance on ISDD and AI-TOD datasets, verifying its robustness.