Chunhui Liu

Jinbin Bai, Chunhui Liu, Feiyue Ni et al.

Video-text retrieval is a class of cross-modal representation learning problems, where the goal is to select the video which corresponds to the text query between a given text query and a pool of candidate videos. The contrastive paradigm of vision-language pretraining has shown promising success with large-scale datasets and unified transformer architecture, and demonstrated the power of a joint latent space. Despite this, the intrinsic divergence between the visual domain and textual domain is still far from being eliminated, and projecting different modalities into a joint latent space might result in the distorting of the information inside the single modality. To overcome the above issue, we present a novel mechanism for learning the translation relationship from a source modality space $\mathcal{S}$ to a target modality space $\mathcal{T}$ without the need for a joint latent space, which bridges the gap between visual and textual domains. Furthermore, to keep cycle consistency between translations, we adopt a cycle loss involving both forward translations from $\mathcal{S}$ to the predicted target space $\mathcal{T'}$, and backward translations from $\mathcal{T'}$ back to $\mathcal{S}$. Extensive experiments conducted on MSR-VTT, MSVD, and DiDeMo datasets demonstrate the superiority and effectiveness of our LaT approach compared with vanilla state-of-the-art methods.

Zining Fang, Chunhui Liu, Bin Xu et al.

Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

Yu Sun, Yin Li, Ruixiao Sun et al.

Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems for content understanding and relevance ranking. Enhancing labeled training data quality and cross-modal fusion significantly improves model performance, influencing key metrics such as quality view rates and ad revenue. High-quality annotations are crucial for advancing content modeling, yet traditional statistical-based active learning (AL) methods face limitations: they struggle to detect overconfident misclassifications and are less effective in distinguishing semantically similar items in deep neural networks. Additionally, audio information plays an increasing role, especially in short-video platforms, yet most pre-trained multimodal architectures primarily focus on text and images. While training from scratch across all three modalities is possible, it sacrifices the benefits of leveraging existing pre-trained visual-language (VL) and audio models. To address these challenges, we propose kNN-based Latent Space Broadening (LSB) to enhance AL efficiency and Vision-Language Modeling with Audio Enhancement (VLMAE), a mid-fusion approach integrating audio into VL models. This system deployed in production systems, leading to significant business gains.

Nan Li, Qi Sun, Lehan Wang et al.

Artificial Intelligence/Machine Learning (AI/ML) has become the most certain and prominent feature of 6G mobile networks. Unlike 5G, where AI/ML was not natively integrated but rather an add-on feature over existing architecture, 6G shall incorporate AI from the onset to address its complexity and support ubiquitous AI applications. Based on our extensive mobile network operation and standardization experience from 2G to 5G, this paper explores the design and standardization principles of AI-Native radio access networks (RAN) for 6G, with a particular focus on its critical Day 1 architecture, functionalities and capabilities. We investigate the framework of AI-Native RAN and present its three essential capabilities to shed some light on the standardization direction; namely, AI-driven RAN processing/optimization/automation, reliable AI lifecycle management (LCM), and AI-as-a-Service (AIaaS) provisioning. The standardization of AI-Native RAN, in particular the Day 1 features, including an AI-Native 6G RAN architecture, were proposed. For validation, a large-scale field trial with over 5000 5G-A base stations have been built and delivered significant improvements in average air interface latency, root cause identification, and network energy consumption with the proposed architecture and the supporting AI functions. This paper aims to provide a Day 1 framework for 6G AI-Native RAN standardization design, balancing technical innovation with practical deployment.

Zhe Wang, Hao Chen, Xinyu Li et al.

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. SSCAP leverages Self-Supervised learning to extract distinguishable features and then applies a novel Co-occurrence Action Parsing algorithm to not only capture the correlation among sub-actions underlying the structure of activities, but also estimate the temporal path of the sub-actions in an accurate and general way. We evaluate on both classic datasets (Breakfast, 50Salads) and the emerging fine-grained action dataset (FineGym) with more complex activity structures and similar sub-actions. Results show that SSCAP achieves state-of-the-art performance on all datasets and can even outperform some weakly-supervised approaches, demonstrating its effectiveness and generalizability.

Yanyi Zhang, Xinyu Li, Chunhui Liu et al.

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3$\times$ while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention ($pool_{topK\_std}$), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.

Jiaojiao Zhao, Yanyi Zhang, Xinyu Li et al.

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.

Chunhui Liu, Xinyu Li, Hao Chen et al.

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed videos, and illustrate that one action model can also cover then informative region by dropping non-informative features. We present Selective Feature Compression (SFC), an action recognition inference strategy that greatly increase model inference efficiency without any accuracy compromise. Differently from previous works that compress kernel sizes and decrease the channel dimension, we propose to compress feature flow at spatio-temporal dimension without changing any backbone parameters. Our experiments on Kinetics-400, UCF101 and ActivityNet show that SFC is able to reduce inference speed by 6-7x and memory usage by 5-6x compared with the commonly used 30 crops dense sampling procedure, while also slightly improving Top1 Accuracy. We thoroughly quantitatively and qualitatively evaluate SFC and all its components and show how does SFC learn to attend to important video regions and to drop temporal features that are uninformative for the task of action recognition.

Xinyu Li, Chunhui Liu, Bing Shuai et al.

In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip (along the temporal dimension). However, not all parts of a video are equally important to determine the action in the clip. In this work, we focus instead on learning where to extract features, so as to focus on the most informative parts of the video. We propose a method called the non-uniform temporal aggregation (NUTA), which aggregates features only from informative temporal segments. We also introduce a synchronization method that allows our NUTA features to be temporally aligned with traditional uniformly sampled video features, so that both local and clip-level features can be combined. Our model has achieved state-of-the-art performance on four widely used large-scale action-recognition datasets (Kinetics400, Kinetics700, Something-something V2 and Charades). In addition, we have created a visualization to illustrate how the proposed NUTA method selects only the most relevant parts of a video clip.

Yi Zhu, Xinyu Li, Chunhui Liu et al.

Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets that influenced the design of models. Then we present video action recognition models in chronological order: starting with early attempts at adapting deep learning, then to the two-stream networks, followed by the adoption of 3D convolutional kernels, and finally to the recent compute-efficient models. In addition, we benchmark popular methods on several representative datasets and release code for reproducibility. In the end, we discuss open problems and shed light on opportunities for video action recognition to facilitate new research ideas.

Ye Li, Guangqiang Yin, Chunhui Liu et al.

Mining the shared features of same identity in different scene, and the unique features of different identity in same scene, are most significant challenges in the field of person re-identification (ReID). Online Instance Matching (OIM) loss function and Triplet loss function are main methods for person ReID. Unfortunately, both of them have drawbacks. OIM loss treats all samples equally and puts no emphasis on hard samples. Triplet loss processes batch construction in a complicated and fussy way and converges slowly. For these problems, we propose a Triplet Online Instance Matching (TOIM) loss function, which lays emphasis on the hard samples and improves the accuracy of person ReID effectively. It combines the advantages of OIM loss and Triplet loss and simplifies the process of batch construction, which leads to a more rapid convergence. It can be trained on-line when handle the joint detection and identification task. To validate our loss function, we collect and annotate a large-scale benchmark dataset (UESTC-PR) based on images taken from surveillance cameras, which contains 499 identities and 60,437 images. We evaluated our proposed loss function on Duke, Marker-1501 and UESTC-PR using ResNet-50, and the result shows that our proposed loss function outperforms the baseline methods by a maximum of 21.7%, including Softmax loss, OIM loss and Triplet loss.

Victor Fragoso, Chunhui Liu, Aayush Bansal et al.

We present compositional nearest neighbors (CompNN), a simple approach to visually interpreting distributed representations learned by a convolutional neural network (CNN) for pixel-level tasks (e.g., image synthesis and segmentation). It does so by reconstructing both a CNN's input and output image by copy-pasting corresponding patches from the training set with similar feature embeddings. To do so efficiently, it makes of a patch-match-based algorithm that exploits the fact that the patch representations learned by a CNN for pixel level tasks vary smoothly. Finally, we show that CompNN can be used to establish semantic correspondences between two images and control properties of the output image by modifying the images contained in the training set. We present qualitative and quantitative experiments for semantic segmentation and image-to-image translation that demonstrate that CompNN is a good tool for interpreting the embeddings learned by pixel-level CNNs.

Chunhui Liu, Yueyu Hu, Yanghao Li et al.

Despite the fact that many 3D human activity benchmarks being proposed, most existing action datasets focus on the action recognition tasks for the segmented videos. There is a lack of standard large-scale benchmarks, especially for current popular data-hungry deep learning based methods. In this paper, we introduce a new large scale benchmark (PKU-MMD) for continuous multi-modality 3D human action understanding and cover a wide range of complex human activities with well annotated information. PKU-MMD contains 1076 long video sequences in 51 action categories, performed by 66 subjects in three camera views. It contains almost 20,000 action instances and 5.4 million frames in total. Our dataset also provides multi-modality data sources, including RGB, depth, Infrared Radiation and Skeleton. With different modalities, we conduct extensive experiments on our dataset in terms of two scenarios and evaluate different methods by various metrics, including a new proposed evaluation protocol 2D-AP. We believe this large-scale dataset will benefit future researches on action detection for the community.