Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos are inherently complex, making overall scoring notoriously difficult. In this paper, we emphasize the critical importance of integrating fine-grained reasoning into video evaluation. We propose FingER, a novel entity-level reasoning evaluation framework that first automatically generates Fine-grained Entity-level questions, and then answers those questions by a Reasoning model with scores, which can be subsequently weighted summed to an overall score for different applications. Specifically, we leverage LLMs to derive entity-level questions across five distinct perspectives, which (i) often focus on some specific entities of the content, thereby making answering or scoring much easier for MLLMs, and (ii) are more interpretable. Then we construct a FingER dataset, consisting of approximately 3.3k videos and corresponding 60k fine-grained QA annotations, each with detailed reasons. Based on that, we further investigate various training protocols to best incentivize the reasoning capability of MLLMs for correct answer prediction. Extensive experiments demonstrate that a reasoning model trained using GRPO with a cold-start strategy achieves the best performance. Notably, our model surpasses existing methods by a relative margin of 11.8% on GenAI-Bench and 5.5% on MonetBench with only 3.3k training videos, which is at most one-tenth of the training samples utilized by other methods. Our codes and datasets have been released.

Estimating 3D poses of multiple humans in real-time is a classic but still challenging task in computer vision. Its major difficulty lies in the ambiguity in cross-view association of 2D poses and the huge state space when there are multiple people in multiple views. In this paper, we present a novel solution for multi-human 3D pose estimation from multiple calibrated camera views. It takes 2D poses in different camera coordinates as inputs and aims for the accurate 3D poses in the global coordinate. Unlike previous methods that associate 2D poses among all pairs of views from scratch at every frame, we exploit the temporal consistency in videos to match the 2D inputs with 3D poses directly in 3-space. More specifically, we propose to retain the 3D pose for each person and update them iteratively via the cross-view multi-human tracking. This novel formulation improves both accuracy and efficiency, as we demonstrated on widely-used public datasets. To further verify the scalability of our method, we propose a new large-scale multi-human dataset with 12 to 28 camera views. Without bells and whistles, our solution achieves 154 FPS on 12 cameras and 34 FPS on 28 cameras, indicating its ability to handle large-scale real-world applications. The proposed dataset will be released at https://github.com/longcw/crossview_3d_pose_tracking.

It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight pedestrian detector, which significantly reduces the computational cost and still holds the high accuracy at the same time. Following the `teacher-student' diagram that a stronger, deeper neural network can teach a lightweight network to learn better representations, we explore multiple knowledge distillation architectures and reframe this approach as a unified, hierarchical distillation framework. In particular, the proposed distillation is performed at multiple hierarchies, multiple stages in a modern detector, which empowers the student detector to learn both low-level details and high-level abstractions simultaneously. Experiment result shows that a student model trained by our framework, with 6 times compression in number of parameters, still achieves competitive performance as the teacher model on the widely used pedestrian detection benchmark.

Multi-object tracking (MOT) has wide applications in the fields of video analysis and signal processing. A major challenge in MOT is how to associate the noisy detections into long and continuous trajectories. In this letter, we address the association problem at the tracklet-level, and mainly focus on the appearance representation designed for tracklets. A multitask convolutional neural network is proposed to learn the discriminative features and spatial-temporal attentions jointly. In particular, we decompose an object in a static image with spatial attentions, and then aggregate multiple features in a tracklet based on the temporal attentions. Appearance misalignment that caused by occlusion and inaccurate bounding is then mitigated by multi-feature aggregation. Experimental results on two challenging MOT benchmarks have demonstrated the effectiveness of the proposed method and shown significant improvement on the quality of tracking identities.