Yang Bai

Yang Bai, Desen Zhou, Songyang Zhang et al.

Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for score regression or ranking, which limits the generalization to capture fine-grained intra-class variation. To overcome the above limitation, we propose a temporal parsing transformer to decompose the holistic feature into temporal part-level representations. Specifically, we utilize a set of learnable queries to represent the atomic temporal patterns for a specific action. Our decoding process converts the frame representations to a fixed number of temporally ordered part representations. To obtain the quality score, we adopt the state-of-the-art contrastive regression based on the part representations. Since existing AQA datasets do not provide temporal part-level labels or partitions, we propose two novel loss functions on the cross attention responses of the decoder: a ranking loss to ensure the learnable queries to satisfy the temporal order in cross attention and a sparsity loss to encourage the part representations to be more discriminative. Extensive experiments show that our proposed method outperforms prior work on three public AQA benchmarks by a considerable margin.

Yiwu Zhong, Licheng Yu, Yang Bai et al.

The abundance of instructional videos and their narrations over the Internet offers an exciting avenue for understanding procedural activities. In this work, we propose to learn video representation that encodes both action steps and their temporal ordering, based on a large-scale dataset of web instructional videos and their narrations, without using human annotations. Our method jointly learns a video representation to encode individual step concepts, and a deep probabilistic model to capture both temporal dependencies and immense individual variations in the step ordering. We empirically demonstrate that learning temporal ordering not only enables new capabilities for procedure reasoning, but also reinforces the recognition of individual steps. Our model significantly advances the state-of-the-art results on step classification (+2.8% / +3.3% on COIN / EPIC-Kitchens) and step forecasting (+7.4% on COIN). Moreover, our model attains promising results in zero-shot inference for step classification and forecasting, as well as in predicting diverse and plausible steps for incomplete procedures. Our code is available at https://github.com/facebookresearch/ProcedureVRL.

Zhichao Liu, Leshan Wang, Desen Zhou et al.

Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an initial prediction to action segments for global context modeling. However, the generated segment representations are often noisy and exhibit inaccurate segment boundaries, over-segmentation and other problems. To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising. The main idea is to denoise segment representations using attention between segment and frame representations, and also use inter-segment attention to capture temporal correlations between segments. The refined segment representations are used to predict action labels and adjust segment boundaries, and a final action segmentation is produced based on voting from segment masks. We show that this novel architecture achieves state-of-the-art accuracy on the popular 50Salads, GTEA and Breakfast benchmarks. We also conduct extensive ablations to demonstrate the effectiveness of different components of our design.

Xingyu Miao, Yang Bai, Haoran Duan et al.

Self-supervised monocular depth estimation methods typically rely on the reprojection error to capture geometric relationships between successive frames in static environments. However, this assumption does not hold in dynamic objects in scenarios, leading to errors during the view synthesis stage, such as feature mismatch and occlusion, which can significantly reduce the accuracy of the generated depth maps. To address this problem, we propose a novel dynamic cost volume that exploits residual optical flow to describe moving objects, improving incorrectly occluded regions in static cost volumes used in previous work. Nevertheless, the dynamic cost volume inevitably generates extra occlusions and noise, thus we alleviate this by designing a fusion module that makes static and dynamic cost volumes compensate for each other. In other words, occlusion from the static volume is refined by the dynamic volume, and incorrect information from the dynamic volume is eliminated by the static volume. Furthermore, we propose a pyramid distillation loss to reduce photometric error inaccuracy at low resolutions and an adaptive photometric error loss to alleviate the flow direction of the large gradient in the occlusion regions. We conducted extensive experiments on the KITTI and Cityscapes datasets, and the results demonstrate that our model outperforms previously published baselines for self-supervised monocular depth estimation.

Xingyu Miao, Yang Bai, Haoran Duan et al.

The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such as DynamicNeRF, have shown impressive performance by leveraging time-varying dynamic radiation fields. However, these methods have limitations when it comes to accurately modeling the motion of complex objects, which can lead to inaccurate and blurry renderings of details. To address this limitation, we propose a novel approach that builds upon a recent generalization NeRF, which aggregates nearby views onto new viewpoints. However, such methods are typically only effective for static scenes. To overcome this challenge, we introduce a module that operates in both the time and frequency domains to aggregate the features of object motion. This allows us to learn the relationship between frames and generate higher-quality images. Our experiments demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets. Specifically, our approach outperforms existing methods in terms of both the accuracy and visual quality of the synthesized views. Our code is available on https://github.com/xingy038/CTNeRF.

Wanfang Su, Lixing Chen, Yang Bai et al.

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

Xingyu Miao, Haoran Duan, Yang Bai et al.

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segmentation of 3D scenes using text. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy. Moreover, to enhance the accuracy of segmentation edges, this work presents a low-rank transient query attention mechanism. To ensure the consistency of segmentation for similar colors under different viewpoints, we convert the segmentation task into a classification task through label volume, which significantly improves the consistency of segmentation in color-similar areas. We also propose a simplified text augmentation strategy to alleviate the issue of ambiguity in the correspondence between CLIP features and text. Extensive experimental results show that our method surpasses current state-of-the-art technologies in both training speed and performance. Our code is available on: https://github.com/xingy038/Laser.git.

Xiaoyu Pan, Yang Bai, Ke Zou et al.

Medical Large Language Models (MLLMs) play a crucial role in ophthalmic diagnosis, holding significant potential to address vision-threatening diseases. However, their accuracy is constrained by hallucinations stemming from limited ophthalmic knowledge, insufficient visual localization and reasoning capabilities, and a scarcity of multimodal ophthalmic data, which collectively impede precise lesion detection and disease diagnosis. Furthermore, existing medical benchmarks fail to effectively evaluate various types of hallucinations or provide actionable solutions to mitigate them. To address the above challenges, we introduce EH-Benchmark, a novel ophthalmology benchmark designed to evaluate hallucinations in MLLMs. We categorize MLLMs' hallucinations based on specific tasks and error types into two primary classes: Visual Understanding and Logical Composition, each comprising multiple subclasses. Given that MLLMs predominantly rely on language-based reasoning rather than visual processing, we propose an agent-centric, three-phase framework, including the Knowledge-Level Retrieval stage, the Task-Level Case Studies stage, and the Result-Level Validation stage. Experimental results show that our multi-agent framework significantly mitigates both types of hallucinations, enhancing accuracy, interpretability, and reliability. Our project is available at https://github.com/ppxy1/EH-Benchmark.

Xingyu Miao, Yang Bai, Haoran Duan et al.

Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition. This work aims to achieve zero-shot controlled stylization in 3D scenes utilizing text or visual input as conditioning factors. We introduce ConRF, a novel method of zero-shot stylization. Specifically, due to the ambiguity of CLIP features, we employ a conversion process that maps the CLIP feature space to the style space of a pre-trained VGG network and then refine the CLIP multi-modal knowledge into a style transfer neural radiation field. Additionally, we use a 3D volumetric representation to perform local style transfer. By combining these operations, ConRF offers the capability to utilize either text or images as references, resulting in the generation of sequences with novel views enhanced by global or local stylization. Our experiment demonstrates that ConRF outperforms other existing methods for 3D scene and single-text stylization in terms of visual quality.

Ayushi Mishra, Yang Bai, Priyadarshan Narayanasamy et al.

Integrating spatial context into large language models (LLMs) has the potential to revolutionize human-computer interaction, particularly in wearable devices. In this work, we present a novel system architecture that incorporates spatial speech understanding into LLMs, enabling contextually aware and adaptive applications for wearable technologies. Our approach leverages microstructure-based spatial sensing to extract precise Direction of Arrival (DoA) information using a monaural microphone. To address the lack of existing dataset for microstructure-assisted speech recordings, we synthetically create a dataset called OmniTalk by using the LibriSpeech dataset. This spatial information is fused with linguistic embeddings from OpenAI's Whisper model, allowing each modality to learn complementary contextual representations. The fused embeddings are aligned with the input space of LLaMA-3.2 3B model and fine-tuned with lightweight adaptation technique LoRA to optimize for on-device processing. SING supports spatially-aware automatic speech recognition (ASR), achieving a mean error of $25.72^\circ$-a substantial improvement compared to the 88.52$^\circ$ median error in existing work-with a word error rate (WER) of 5.3. SING also supports soundscaping, for example, inference how many people were talking and their directions, with up to 5 people and a median DoA error of 16$^\circ$. Our system demonstrates superior performance in spatial speech understanding while addressing the challenges of power efficiency, privacy, and hardware constraints, paving the way for advanced applications in augmented reality, accessibility, and immersive experiences.

Yang Bai, Lixing Chen, Shaolei Ren et al.

The rapid uptake of intelligent applications is pushing deep learning (DL) capabilities to Internet-of-Things (IoT). Despite the emergence of new tools for embedding deep neural networks (DNNs) into IoT devices, providing satisfactory Quality of Experience (QoE) to users is still challenging due to the heterogeneity in DNN architectures, IoT devices, and user preferences. This paper studies automated customization for DL inference on IoT devices (termed as on-thing inference), and our goal is to enhance user QoE by configuring the on-thing inference with an appropriate DNN for users under different usage scenarios. The core of our method is a DNN selection module that learns user QoE patterns on-the-fly and identifies the best-fit DNN for on-thing inference with the learned knowledge. It leverages a novel online learning algorithm, NeuralUCB, that has excellent generalization ability for handling various user QoE patterns. We also embed the knowledge transfer technique in NeuralUCB to expedite the learning process. However, NeuralUCB frequently solicits QoE ratings from users, which incurs non-negligible inconvenience. To address this problem, we design feedback solicitation schemes to reduce the number of QoE solicitations while maintaining the learning efficiency of NeuralUCB. A pragmatic problem, aggregated QoE, is further investigated to improve the practicality of our framework. We conduct experiments on both synthetic and real-world data. The results indicate that our method efficiently learns the user QoE pattern with few solicitations and provides drastic QoE enhancement for IoT devices.

Yang Bai, Yu Guan, Jian Qing Shi et al.

Fatigue is a broad, multifactorial concept that includes the subjective perception of reduced physical and mental energy levels. It is also one of the key factors that strongly affect patients' health-related quality of life. To date, most fatigue assessment methods were based on self-reporting, which may suffer from many factors such as recall bias. To address this issue, in this work, we recorded multi-modal physiological data (including ECG, accelerometer, skin temperature and respiratory rate, as well as demographic information such as age, BMI) in free-living environments and developed automated fatigue assessment models. Specifically, we extracted features from each modality and employed the random forest-based mixed-effects models, which can take advantage of the demographic information for improved performance. We conducted experiments on our collected dataset, and very promising preliminary results were achieved. Our results suggested ECG played an important role in the fatigue assessment tasks.