Haozhi Cao

Yuecong Xu, Haozhi Cao, Zhenghua Chen et al.

Video analysis tasks such as action recognition have received increasing research interest with growing applications in fields such as smart healthcare, thanks to the introduction of large-scale datasets and deep learning-based representations. However, video models trained on existing datasets suffer from significant performance degradation when deployed directly to real-world applications due to domain shifts between the training public video datasets (source video domains) and real-world videos (target video domains). Further, with the high cost of video annotation, it is more practical to use unlabeled videos for training. To tackle performance degradation and address concerns in high video annotation cost uniformly, the video unsupervised domain adaptation (VUDA) is introduced to adapt video models from the labeled source domain to the unlabeled target domain by alleviating video domain shift, improving the generalizability and portability of video models. This paper surveys recent progress in VUDA with deep learning. We begin with the motivation of VUDA, followed by its definition, and recent progress of methods for both closed-set VUDA and VUDA under different scenarios, and current benchmark datasets for VUDA research. Eventually, future directions are provided to promote further VUDA research. The repository of this survey is provided at https://github.com/xuyu0010/awesome-video-domain-adaptation.

Haozhi Cao, Yuecong Xu, Jianfei Yang et al.

Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a practical solution to embed semantic understanding in autonomous systems without expensive point-wise annotations. While previous MM-UDA methods can achieve overall improvement, they suffer from significant class-imbalanced performance, restricting their adoption in real applications. This imbalanced performance is mainly caused by: 1) self-training with imbalanced data and 2) the lack of pixel-wise 2D supervision signals. In this work, we propose Multi-modal Prior Aided (MoPA) domain adaptation to improve the performance of rare objects. Specifically, we develop Valid Ground-based Insertion (VGI) to rectify the imbalance supervision signals by inserting prior rare objects collected from the wild while avoiding introducing artificial artifacts that lead to trivial solutions. Meanwhile, our SAM consistency loss leverages the 2D prior semantic masks from SAM as pixel-wise supervision signals to encourage consistent predictions for each object in the semantic mask. The knowledge learned from modal-specific prior is then shared across modalities to achieve better rare object segmentation. Extensive experiments show that our method achieves state-of-the-art performance on the challenging MM-UDA benchmark. Code will be available at https://github.com/AronCao49/MoPA.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environments. However, these methods require constant access to source data during the adaptation process. Yet in many real-world applications, subjects and scenes in the source video domain should be irrelevant to those in the target video domain. With the increasing emphasis on data privacy, such methods that require source data access would raise serious privacy issues. Therefore, to cope with such concern, a more practical domain adaptation scenario is formulated as the Source-Free Video-based Domain Adaptation (SFVDA). Though there are a few methods for Source-Free Domain Adaptation (SFDA) on image data, these methods yield degenerating performance in SFVDA due to the multi-modality nature of videos, with the existence of additional temporal features. In this paper, we propose a novel Attentive Temporal Consistent Network (ATCoN) to address SFVDA by learning temporal consistency, guaranteed by two novel consistency objectives, namely feature consistency and source prediction consistency, performed across local temporal features. ATCoN further constructs effective overall temporal features by attending to local temporal features based on prediction confidence. Empirical results demonstrate the state-of-the-art performance of ATCoN across various cross-domain action recognition benchmarks.

Haozhi Cao, Yuecong Xu, Jianfei Yang et al.

Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation (MM-CTTA) as a new extension of CTTA for 3D semantic segmentation. The key to MM-CTTA is to adaptively attend to the reliable modality while avoiding catastrophic forgetting during continual domain shifts, which is out of the capability of previous TTA or CTTA methods. To fulfill this gap, we propose an MM-CTTA method called Continual Cross-Modal Adaptive Clustering (CoMAC) that addresses this task from two perspectives. On one hand, we propose an adaptive dual-stage mechanism to generate reliable cross-modal predictions by attending to the reliable modality based on the class-wise feature-centroid distance in the latent space. On the other hand, to perform test-time adaptation without catastrophic forgetting, we design class-wise momentum queues that capture confident target features for adaptation while stochastically restoring pseudo-source features to revisit source knowledge. We further introduce two new benchmarks to facilitate the exploration of MM-CTTA in the future. Our experimental results show that our method achieves state-of-the-art performance on both benchmarks.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

To enable video models to be applied seamlessly across video tasks in different environments, various Video Unsupervised Domain Adaptation (VUDA) methods have been proposed to improve the robustness and transferability of video models. Despite improvements made in model robustness, these VUDA methods require access to both source data and source model parameters for adaptation, raising serious data privacy and model portability issues. To cope with the above concerns, this paper firstly formulates Black-box Video Domain Adaptation (BVDA) as a more realistic yet challenging scenario where the source video model is provided only as a black-box predictor. While a few methods for Black-box Domain Adaptation (BDA) are proposed in image domain, these methods cannot apply to video domain since video modality has more complicated temporal features that are harder to align. To address BVDA, we propose a novel Endo and eXo-TEmporal Regularized Network (EXTERN) by applying mask-to-mix strategies and video-tailored regularizations: endo-temporal regularization and exo-temporal regularization, performed across both clip and temporal features, while distilling knowledge from the predictions obtained from the black-box predictor. Empirical results demonstrate the state-of-the-art performance of EXTERN across various cross-domain closed-set and partial-set action recognition benchmarks, which even surpassed most existing video domain adaptation methods with source data accessibility.

Tao Wu, Chuhao Zhou, Guangyu Zhao et al.

Embodied Question Answering (EQA) requires an agent to interpret language, perceive its environment, and navigate within 3D scenes to produce responses. Existing EQA benchmarks assume that every question must be answered, but embodied agents should know when they do not have sufficient information to answer. In this work, we focus on a minimal requirement for EQA agents, abstention: knowing when to withhold an answer. From an initial study of 500 human queries, we find that 32.4% contain missing or underspecified context. Drawing on this initial study and cognitive theories of human communication errors, we derive five representative categories requiring abstention: actionability limitation, referential underspecification, preference dependence, information unavailability, and false presupposition. We augment OpenEQA by having annotators transform well-posed questions into ambiguous variants outlined by these categories. The resulting dataset, AbstainEQA, comprises 1,636 annotated abstention cases paired with 1,636 original OpenEQA instances for balanced evaluation. Evaluating on AbstainEQA, we find that even the best frontier model only attains 42.79% abstention recall, while humans achieve 91.17%. We also find that scaling, prompting, and reasoning only yield marginal gains, and that fine-tuned models overfit to textual cues. Together, these results position abstention as a fundamental prerequisite for reliable interaction in embodied settings and as a necessary basis for effective clarification.

Thien-Minh Nguyen, Shenghai Yuan, Thien Hoang Nguyen et al.

Perception plays a crucial role in various robot applications. However, existing well-annotated datasets are biased towards autonomous driving scenarios, while unlabelled SLAM datasets are quickly over-fitted, and often lack environment and domain variations. To expand the frontier of these fields, we introduce a comprehensive dataset named MCD (Multi-Campus Dataset), featuring a wide range of sensing modalities, high-accuracy ground truth, and diverse challenging environments across three Eurasian university campuses. MCD comprises both CCS (Classical Cylindrical Spinning) and NRE (Non-Repetitive Epicyclic) lidars, high-quality IMUs (Inertial Measurement Units), cameras, and UWB (Ultra-WideBand) sensors. Furthermore, in a pioneering effort, we introduce semantic annotations of 29 classes over 59k sparse NRE lidar scans across three domains, thus providing a novel challenge to existing semantic segmentation research upon this largely unexplored lidar modality. Finally, we propose, for the first time to the best of our knowledge, continuous-time ground truth based on optimization-based registration of lidar-inertial data on large survey-grade prior maps, which are also publicly released, each several times the size of existing ones. We conduct a rigorous evaluation of numerous state-of-the-art algorithms on MCD, report their performance, and highlight the challenges awaiting solutions from the research community.

Kuan Xu, Zeyu Jiang, Haozhi Cao et al.

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in handling repetitive textures and meaningless areas due to their reliance on implicit triangulation. In this paper, we propose an efficient and accurate SCR system. Compared to existing SCR methods, we propose a unified architecture for both scene encoding and salient keypoint detection, allowing our system to prioritize the encoding of informative regions. This design significantly improves computational efficiency. Additionally, we introduce a mechanism that utilizes sequential information during both mapping and relocalization. The proposed method enhances the implicit triangulation, especially in environments with repetitive textures. Comprehensive experiments conducted across indoor and outdoor datasets demonstrate that the proposed system outperforms state-of-the-art (SOTA) SCR methods. Our single-frame relocalization mode improves the recall rate of our baseline by 6.4% and increases the running speed from 56Hz to 90Hz. Furthermore, our sequence-based mode increases the recall rate by 11% while maintaining the original efficiency.

Geng Li, Haozhi Cao, Mingyang Liu et al.

Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance when trained on large-scale, high-quality datasets, these datasets are prohibitively expensive to collect and annotate, e.g., organ data in authentic medical scenarios. With insufficient training samples and data noise, existing methods degrade significantly since non-rigid patterns are more flexible and complicated than rigid ones, and the distributions across samples are more distinct, leading to higher difficulty in representation learning with few data. In this work, we aim to deal with this challenging few-shot non-rigid point cloud registration problem. Based on the observation that complex non-rigid transformation patterns can be decomposed into rigid and small non-rigid transformations, we propose a novel and effective framework, UniRiT. UniRiT adopts a two-step registration strategy that first aligns the centroids of the source and target point clouds and then refines the registration with non-rigid transformations, thereby significantly reducing the problem complexity. To validate the performance of UniRiT on real-world datasets, we introduce a new dataset, MedMatch3D, which consists of real human organs and exhibits high variability in sample distribution. We further establish a new challenging benchmark for few-shot non-rigid registration. Extensive empirical results demonstrate that UniRiT achieves state-of-the-art performance on MedMatch3D, improving the existing best approach by 94.22%.

Chuhao Zhou, Chenxi Jiang, Yi Xie et al.

Dataset Distillation (DD) seeks to create a condensed dataset that, when used to train a model, enables the model to achieve performance similar to that of a model trained on the entire original dataset. It relieves the model training from processing massive data and thus reduces the computation resources, storage, and time costs. This paper illustrates our solution that ranks 1st in the ECCV-2024 Data Distillation Challenge (track 1). Our solution, Modified Difficulty-Aligned Trajectory Matching (M-DATM), introduces two key modifications to the original state-of-the-art method DATM: (1) the soft labels learned by DATM do not achieve one-to-one correspondence with the counterparts generated by the official evaluation script, so we remove the soft labels technique to alleviate such inconsistency; (2) since the removal of soft labels makes it harder for the synthetic dataset to learn late trajectory information, particularly on Tiny ImageNet, we reduce the matching range, allowing the synthetic data to concentrate more on the easier patterns. In the final evaluation, our M-DATM achieved accuracies of 0.4061 and 0.1831 on the CIFAR-100 and Tiny ImageNet datasets, ranking 1st in the Fixed Images Per Class (IPC) Track.

Pengyu Yin, Shenghai Yuan, Haozhi Cao et al.

We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registration-based methods have shown promising performance improvements in global localization compared with geometric-only methods, landmarks can be repetitive and misleading for correspondence establishment. We propose to mitigate this problem by modeling semantic distributions with continuous functions learned from a population of Gaussian processes. Compared with discrete semantic labels, the continuous functions capture finer-grained geo-semantic information and also provide more detailed metric information for correspondence establishment. We insert this continuous function as the middle layer between the object layer and the metric-semantic layer, forming a tri-layered 3D scene graph, serving as a light-weight yet performant backend for one-shot localization. We term our global localization pipeline Outram-GSF (Gaussian semantic field) and conduct a wide range of experiments on publicly available data sets, validating the superior performance against the current state-of-the-art.

Rui Qian, Haozhi Cao, Tianchen Deng et al.

Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While recent object-centric paradigms significantly improve efficiency by leveraging flexible 3D Gaussian primitives, they still rely heavily on a large number of randomly initialized primitives, which inevitably leads to 1) inefficient primitive initialization and 2) outlier primitives that introduce erroneous artifacts. In this paper, we propose SplatSSC, a novel framework that resolves these limitations with a depth-guided initialization strategy and a principled Gaussian aggregator. Instead of random initialization, SplatSSC utilizes a dedicated depth branch composed of a Group-wise Multi-scale Fusion (GMF) module, which integrates multi-scale image and depth features to generate a sparse yet representative set of initial Gaussian primitives. To mitigate noise from outlier primitives, we develop the Decoupled Gaussian Aggregator (DGA), which enhances robustness by decomposing geometric and semantic predictions during the Gaussian-to-voxel splatting process. Complemented with a specialized Probability Scale Loss, our method achieves state-of-the-art performance on the Occ-ScanNet dataset, outperforming prior approaches by over 6.3% in IoU and 4.1% in mIoU, while reducing both latency and memory consumption by more than 9.3%. The code will be released upon acceptance.

Haozhi Cao, Yuecong Xu, Pengyu Yin et al.

Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by leveraging self-refinement per frame, they suffer from two major limitations: 1) unstable frame-wise predictions caused by temporal inconsistency, and 2) consistently incorrect predictions that violate the assumption of reliable modality guidance. To address these limitations, this work introduces a comprehensive two-fold framework. Firstly, building upon our previous work ReLiable Spatial-temporal Voxels (Latte), we propose Latte++ that better suppresses the unstable frame-wise predictions with more informative geometric correspondences. Instead of utilizing a universal sliding window, Latte++ employs multi-window aggregation to capture more reliable correspondences to better evaluate the local prediction consistency of different semantic categories. Secondly, to tackle the consistently incorrect predictions, we propose Interactive Test-Time Adaptation (ITTA), a flexible add-on to empower effortless human feedback with existing MM-TTA methods. ITTA introduces a novel human-in-the-loop approach that efficiently integrates minimal human feedback through interactive segmentation, requiring only simple point clicks and bounding box annotations. Instead of using independent interactive networks, ITTA employs a lightweight promptable branch with a momentum gradient module to capture and reuse knowledge from scarce human feedback during online inference. Extensive experiments across five MM-TTA benchmarks demonstrate that ITTA achieves consistent and notable improvements with robust performance gains for target classes of interest in challenging imbalanced scenarios, while Latte++ provides complementary benefits for temporal stability.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

While action recognition (AR) has gained large improvements with the introduction of large-scale video datasets and the development of deep neural networks, AR models robust to challenging environments in real-world scenarios are still under-explored. We focus on the task of action recognition in dark environments, which can be applied to fields such as surveillance and autonomous driving at night. Intuitively, current deep networks along with visual enhancement techniques should be able to handle AR in dark environments, however, it is observed that this is not always the case in practice. To dive deeper into exploring solutions for AR in dark environments, we launched the UG2+ Challenge Track 2 (UG2-2) in IEEE CVPR 2021, with a goal of evaluating and advancing the robustness of AR models in dark environments. The challenge builds and expands on top of a novel ARID dataset, the first dataset for the task of dark video AR, and guides models to tackle such a task in both fully and semi-supervised manners. Baseline results utilizing current AR models and enhancement methods are reported, justifying the challenging nature of this task with substantial room for improvements. Thanks to the active participation from the research community, notable advances have been made in participants' solutions, while analysis of these solutions helped better identify possible directions to tackle the challenge of AR in dark environments.

Haozhi Cao, Yuecong Xu, Jianfei Yang et al.

This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on their comprehensive understanding of videos. Specifically, the training sample, denoted as the incoherent clip, is constructed by multiple sub-clips hierarchically sampled from the same raw video with various lengths of incoherence between each other. The network is trained to learn high-level representation by predicting the location and length of incoherence given the incoherent clip as input. Additionally, intra-video contrastive learning is introduced to maximize the mutual information between incoherent clips from the same raw video. We evaluate our proposed method through extensive experiments on action recognition and video retrieval utilizing various backbone networks. Experiments show that our proposed method achieves state-of-the-art performance across different backbone networks and different datasets compared with previous coherence-based methods.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios. It relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA) that source data are sampled from a single domain and match a uniform data distribution. MSDA is more difficult due to the existence of different domain shifts between distinct domain pairs. When considering videos, the negative transfer would be provoked by spatial-temporal features and can be formulated into a more challenging Multi-Source Video Domain Adaptation (MSVDA) problem. In this paper, we address the MSVDA problem by proposing a novel Temporal Attentive Moment Alignment Network (TAMAN) which aims for effective feature transfer by dynamically aligning both spatial and temporal feature moments. TAMAN further constructs robust global temporal features by attending to dominant domain-invariant local temporal features with high local classification confidence and low disparity between global and local feature discrepancies. To facilitate future research on the MSVDA problem, we introduce comprehensive benchmarks, covering extensive MSVDA scenarios. Empirical results demonstrate a superior performance of the proposed TAMAN across multiple MSVDA benchmarks.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsumes the target one. The key challenge of PDA is the issue of negative transfer caused by source-only classes. For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem. In this paper, we propose a novel Partial Adversarial Temporal Attentive Network (PATAN) to address the PVDA problem by utilizing both spatial and temporal features for filtering source-only classes. Besides, PATAN constructs effective overall temporal features by attending to local temporal features that contribute more toward the class filtration process. We further introduce new benchmarks to facilitate research on PVDA problems, covering a wide range of PVDA scenarios. Empirical results demonstrate the state-of-the-art performance of our proposed PATAN across the multiple PVDA benchmarks.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research towards video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-term dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore we propose a novel Adversarial Correlation Adaptation Network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as Pixel Correlation Discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts. We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification. Empirical results demonstrate the state-of-the-art performance of our proposed ACAN for both existing and the new video DA datasets.

Haozhi Cao, Yuecong Xu, Jianfei Yang et al.

Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require costly key point annotation. In this paper, we propose a novel temporal feature extraction module, named Key Point Shifts Embedding Module ($KPSEM$), to adaptively extract channel-wise key point shifts across video frames without key point annotation for temporal feature extraction. Key points are adaptively extracted as feature points with maximum feature values at split regions, while key point shifts are the spatial displacements of corresponding key points. The key point shifts are encoded as the overall temporal features via linear embedding layers in a multi-set manner. Our method achieves competitive performance through embedding key point shifts with trivial computational cost, achieving the state-of-the-art performance of 82.05% on Mini-Kinetics and competitive performance on UCF101, Something-Something-v1, and HMDB51 datasets.

Yuecong Xu, Haozhi Cao, Jianfei Yang et al.

Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is designed to address this challenge and have shown excellent performance. However, the non-local block brings significant increase in computation cost to the original network. It also lacks the ability to model regional correlation in videos. To address the above limitations, we propose Pyramid Non-Local (PNL) module, which extends the non-local block by incorporating regional correlation at multiple scales through a pyramid structured module. This extension upscales the effectiveness of non-local operation by attending to the interaction between different regions. Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83.09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.

Yuecong Xu, Jianfei Yang, Haozhi Cao et al.

The task of action recognition in dark videos is useful in various scenarios, e.g., night surveillance and self-driving at night. Though progress has been made in the action recognition task for videos in normal illumination, few have studied action recognition in the dark. This is partly due to the lack of sufficient datasets for such a task. In this paper, we explored the task of action recognition in dark videos. We bridge the gap of the lack of data for this task by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset. It consists of over 3,780 video clips with 11 action categories. To the best of our knowledge, it is the first dataset focused on human actions in dark videos. To gain further understandings of our ARID dataset, we analyze the ARID dataset in detail and exhibited its necessity over synthetic dark videos. Additionally, we benchmarked the performance of several current action recognition models on our dataset and explored potential methods for increasing their performances. Our results show that current action recognition models and frame enhancement methods may not be effective solutions for the task of action recognition in dark videos.