Minjie Hua

Minjie Hua, Yibing Nan, Shiguo Lian

Person counting is considered as a fundamental task in video surveillance. However, the scenario diversity in practical applications makes it difficult to exploit a single person counting model for general use. Consequently, engineers must preview the video stream and manually specify an appropriate person counting model based on the scenario of camera shot, which is time-consuming, especially for large-scale deployments. In this paper, we propose a person counting paradigm that utilizes a scenario classifier to automatically select a suitable person counting model for each captured frame. First, the input image is passed through the scenario classifier to obtain a scenario label, which is then used to allocate the frame to one of five fine-tuned models for person counting. Additionally, we present five augmentation datasets collected from different scenarios, including side-view, long-shot, top-view, customized and crowd, which are also integrated to form a scenario classification dataset containing 26323 samples. In our comparative experiments, the proposed paradigm achieves better balance than any single model on the integrated dataset, thus its generalization in various scenarios has been proved.

Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

Kaikai Zhao, Zhaoxiang Liu, Xuejiao Lei et al.

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we presents the first comprehensive evaluation of the DeepSeek and its related models (including DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, DeepSeek-R1-Distill-Llama series, their corresponding 4-bit quantized models, and the reasoning model QwQ-32B) using our enhanced A-Eval benchmark, A-Eval-2.0. Our systematic analysis reveals several key insights: (1) Given identical model architectures and training data, larger parameter models demonstrate superior performance, aligning with the scaling law. However, smaller models may achieve enhanced capabilities when employing optimized training strategies and higher-quality data; (2) Reasoning-enhanced model show significant performance gains in logical reasoning tasks but may underperform in text understanding and generation tasks; (3) As the data difficulty increases, distillation or reasoning enhancements yield higher performance gains for the models. Interestingly, reasoning enhancements can even have a negative impact on simpler problems; (4) Quantization impacts different capabilities unevenly, with significant drop on logical reasoning and minimal impact on text generation. Based on these results and findings, we design an model selection handbook enabling users to select the most cost-effective models without efforts.

Minjie Hua, Yibing Nan, Shiguo Lian

This paper presents a novel obstacle avoidance system for road robots equipped with RGB-D sensor that captures scenes of its way forward. The purpose of the system is to have road robots move around autonomously and constantly without any collision even with small obstacles, which are often missed by existing solutions. For each input RGB-D image, the system uses a new two-stage semantic segmentation network followed by the morphological processing to generate the accurate semantic map containing road and obstacles. Based on the map, the local path planning is applied to avoid possible collision. Additionally, optical flow supervision and motion blurring augmented training scheme is applied to improve temporal consistency between adjacent frames and overcome the disturbance caused by camera shake. Various experiments are conducted to show that the proposed architecture obtains high performance both in indoor and outdoor scenarios.

Minjie Hua, Yibing Nan, Shiguo Lian

This paper presents a novel approach for predicting the falls of people in advance from monocular video. First, all persons in the observed frames are detected and tracked with the coordinates of their body keypoints being extracted meanwhile. A keypoints vectorization method is exploited to eliminate irrelevant information in the initial coordinate representation. Then, the observed keypoint sequence of each person is input to the pose prediction module adapted from sequence-to-sequence(seq2seq) architecture to predict the future keypoint sequence. Finally, the predicted pose is analyzed by the falls classifier to judge whether the person will fall down in the future. The pose prediction module and falls classifier are trained separately and tuned jointly using Le2i dataset, which contains 191 videos of various normal daily activities as well as falls performed by several actors. The contrast experiments with mainstream raw RGB-based models show the accuracy improvement of utilizing body keypoints in falls classification. Moreover, the precognition of falls is proved effective by comparisons between models that with and without the pose prediction module.

Minjie Hua, Fuyuan Shi, Yibing Nan et al.

This paper presents a novel system that enables intelligent robots to exhibit realistic body gestures while communicating with humans. The proposed system consists of a listening model and a speaking model used in corresponding conversational phases. Both models are adapted from the sequence-to-sequence (seq2seq) architecture to synthesize body gestures represented by the movements of twelve upper-body keypoints. All the extracted 2D keypoints are firstly 3D-transformed, then rotated and normalized to discard irrelevant information. Substantial videos of human conversations from Youtube are collected and preprocessed to train the listening and speaking models separately, after which the two models are evaluated using metrics of mean squared error (MSE) and cosine similarity on the test dataset. The tuned system is implemented to drive a virtual avatar as well as Pepper, a physical humanoid robot, to demonstrate the improvement on conversational interaction abilities of our method in practice.

Kai Wang, Yimin Lin, Luowei Wang et al.

This paper presents a novel framework for simultaneously implementing localization and segmentation, which are two of the most important vision-based tasks for robotics. While the goals and techniques used for them were considered to be different previously, we show that by making use of the intermediate results of the two modules, their performance can be enhanced at the same time. Our framework is able to handle both the instantaneous motion and long-term changes of instances in localization with the help of the segmentation result, which also benefits from the refined 3D pose information. We conduct experiments on various datasets, and prove that our framework works effectively on improving the precision and robustness of the two tasks and outperforms existing localization and segmentation algorithms.