Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream. To alleviate long-context decoding overhead, we propose a plug-and-play Geometry-Adaptive Voxel Compression (GAVC) module for efficient visual token compression. To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline that curates over 1M online spatio-temporal 3D QA pairs and establishes a comprehensive benchmark spanning 29 tasks. Extensive experiments show that our approach significantly outperforms both proprietary and open-source models across online and offline 3D spatial understanding, reasoning, and grounding tasks. The project page is available at https://stream3d-vlm.github.io/
Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model
Guangdong Province Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（广东省机器智能与先进计算重点实验室）；Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Peng Cheng Laboratory（鹏城实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（广东省机器智能与先进计算重点实验室）
ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models
Birla Institute of Technology and Science Pilani, K.K Birla Goa Campus（比拉理工学院和科学学院，比拉戈阿校园）；Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore（设计与工程学院机械工程系，新加坡国立大学）
ZeroGUI: Automating Online GUI Learning at Zero Human Cost
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）
China University of Geosciences（中国地质大学）；University of Wollongong（卧龙岗大学）
Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based on the evidence accumulation over time to make predictions from stream videos. This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence. In particular, a fast incremental updating method for the weighted covariance descriptor is developed for accumulation…
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life applications: (1) Learning new classes makes the trained model quickly forget old classes knowledge, which is referred to as catastrophic forgetting. (2) As new observations of old classes come sequentially over time, the distribution may change in unforeseen way, making the performance degrade dramatically on future data, which is referred to as concept drift. …
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Alibaba Group（阿里巴巴集团）；Kyushu University（九州大学）；Tianjin University of Technology（天津理工大学）；Nanyang Technological University（南洋理工大学）
Adversarial attacks of deep neural networks have been intensively studied on image, audio, natural language, patch, and pixel classification tasks. Nevertheless, as a typical, while important real-world application, the adversarial attacks of online video object tracking that traces an object's moving trajectory instead of its category are rarely explored. In this paper, we identify a new task for the adversarial attack to visual tracking: online generating imperceptible perturbations that mislead trackers along an incorrect (Untargeted Attack, UA) or specified trajectory (Targeted Attack, TA)…
NICTA（国家信息与通信技术研究院）；University of New South Wales（新南威尔士大学）；Australian National University（澳大利亚国立大学）
The ability to efficiently and accurately detect objects plays a very crucial role for many computer vision tasks. Recently, offline object detectors have shown a tremendous success. However, one major drawback of offline techniques is that a complete set of training data has to be collected beforehand. In addition, once learned, an offline detector can not make use of newly arriving data. To alleviate these drawbacks, online learning has been adopted with the following objectives: (1) the technique should be computationally and storage efficient; (2) the updated classifier must maintain its h…
In this paper, a new online method based on nonparametric weighted feature extraction (NWFE) is proposed. NWFE was introduced to enjoy optimum characteristics of linear discriminant analysis (LDA) and nonparametric discriminant analysis (NDA) while rectifying their drawbacks. It emphasizes the points near decision boundary by putting greater weights on them and deemphasizes other points. Incremental nonparametric weighted feature extraction (INWFE) is the online version of NWFE. INWFE has advantages of NWFE method such as extracting more than L-1 features in contrast to LDA. It is independent …
Georgia Institute of Technology（佐治亚理工学院）；Transylvania University（特兰西瓦尼亚大学）
This paper proposes a simple yet effective approach to learn visual features online for improving loop-closure detection and place recognition, based on bag-of-words frameworks. The approach learns a codeword in bag-of-words model from a pair of matched features from two consecutive frames, such that the codeword has temporally-derived perspective invariance to camera motion. The learning algorithm is efficient: the binary descriptor is generated from the mean image patch, and the mask is learned based on discriminative projection by minimizing the intra-class distances among the learned featu…
Vehicle relocation is the problem in which a mobile robot has to estimate the self-position with respect to an a priori map of landmarks using the perception and the motion measurements without using any knowledge of the initial self-position. Recently, RANdom SAmple Consensus (RANSAC), a robust multi-hypothesis estimator, has been successfully applied to offline relocation in static environments. On the other hand, online relocation in dynamic environments is still a difficult problem, for available computation time is always limited, and for measurement include many outliers. To realize real…
University of Oxford（牛津大学）；Samsung Research America（三星美国研究院）；Oxford Brookes University（牛津布鲁克斯大学）
Current state-of-the-art action detection systems are tailored for offline batch-processing applications. However, for online applications like human-robot interaction, current systems fall short, either because they only detect one action per video, or because they assume that the entire video is available ahead of time. In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging action videos in which different action categories occur concurrently. In contrast…
Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement
The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；Huazhong University of Science and Technology（华中科技大学）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as catastrophic forgetting problem. The main reason for catastrophic forgetting is that the past concept data is not available and neural weights are changed during incrementally learning new concepts. In this paper, we propose a pseudo-rehearsal based class incremental learning approach to make neural ne…
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉成像工程技术研究中心）
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation task, mainly due to its continuously-evolving semantic label space, partial pixelwise ground-truth annotations, and constrained data availability. To ad- dress this, we propose an incremental learning strategy that can fast adapt deep segmentation models without catastrophic forgetting, using a streaming input data with pixel annotations on the novel classe…
Indian Institute of Technology Kanpur（坎普尔印度理工学院）；Duke University（杜克大学）；Indian Institute of Technology Roorkee（鲁尔基印度理工学院）；University of Bath（巴斯大学）
We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes are given incrementally, which necessitates a class incremental learning approach; (2) Data for each class is given in an online fashion, i.e., each training example is seen only once during training; (3) Each class has very few training examples; and (4) We do not use or assume access to any replay/memory to store data from previous classes. Therefore, in this setting, we have to handle twofold problems of catastroph…
Dalian University of Techonology（大连理工大学）；Dalian Maritime University（大连海事大学）
Traditional face alignment based on machine learning usually tracks the localizations of facial landmarks employing a static model trained offline where all of the training data is available in advance. When new training samples arrive, the static model must be retrained from scratch, which is excessively time-consuming and memory-consuming. In many real-time applications, the training data is obtained one by one or batch by batch. It results in that the static model limits its performance on sequential images with extensive variations. Therefore, the most critical and challenging aspect in th…
GIST（光州科学技术院）；NAVER AI Lab（NAVER人工智能实验室）；Upstage AI Research（Upstage人工智能研究院）；Yonsei University（延世大学）
Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain aspects. For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment. We additionally propose a new metric to better measure the performance of the continual learning methods subject to inference queries at any moment. To address…
Incremental (online) structure from motion pipelines seek to recover the camera matrix associated with an image $I_n$ given $n-1$ images, $I_1,...,I_{n-1}$, whose camera matrices have already been recovered. In this paper, we introduce a novel solution to the six-point online algorithm to recover the exterior parameters associated with $I_n$. Our algorithm uses just six corresponding pairs of 2D points, extracted each from $I_n$ and from \textit{any} of the preceding $n-1$ images, allowing the recovery of the full six degrees of freedom of the $n$'th camera, and unlike common methods, does not…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contri…
AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis
Xidian University（西安电子科技大学）；National University of Singapore（新加坡国立大学）；Northwestern Polytechnical University（西北工业大学）；Singapore Management University（新加坡管理大学）
IIT Kanpur（印度理工学院坎普尔分校）；Duke University（杜克大学）；Verisk Analytics（威斯科分析公司）；University of Bath（巴斯大学）
A wide variety of methods have been developed to enable lifelong learning in conventional deep neural networks. However, to succeed, these methods require a `batch' of samples to be available and visited multiple times during training. While this works well in a static setting, these methods continue to suffer in a more realistic situation where data arrives in \emph{online streaming manner}. We empirically demonstrate that the performance of current approaches degrades if the input is obtained as a stream of data with the following restrictions: $(i)$ each instance comes one at a time and can…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
Online Hyperparameter Optimization for Class-Incremental Learning
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；California Institute of Technology（加州理工学院）；Singapore Management University（新加坡管理大学）
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptiv…
Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos
Johns Hopkins University（约翰斯·霍普金斯大学）；Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克信息学研究所，萨尔兰信息学园区）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Singapore Management University（新加坡管理大学）
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain incremental). One of the key challenges of continual learning is to avoid catastrophic forgetting (CF), i.e., forgetting old tasks in the presence of more recent tasks. Over the past few years, many methods and tricks have been introduced to address this problem, but many have not been fairly and systematically compared under a variety of realistic and practical sett…
