An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.
Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
Southeast University School of Cyber Science and Engineering（东南大学网络安全科学与工程学院）；Southeast University School of Computer Science and Engineering（东南大学计算机科学与工程学院）；Nanjing Normal University School of Electrical Engineering and Automation（南京师范大学电气工程与自动化学院）
University of California, Berkeley（加利福尼亚大学伯克利分校）；National University of Singapore（新加坡国立大学）；Boston University（波士顿大学）
Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video. Our model is end-to-end trainable and can benefit from more few-shot examples. At test time, each proposal is assigned the label of the few-shot activity class corresponding to the maximum …
University of California, Berkeley（加州大学伯克利分校）；Boston University（波士顿大学）；IIT Kharagpur（印度理工学院克勒格布尔分校）
Many interesting events in the real world are rare making preannotated machine learning ready videos a rarity in consequence. Thus, temporal activity detection models that are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection based on proposal regression which detects the start and end time of the activities in untrimmed videos. Our model is end-to-end trainable, takes into account the frame rate differences between few-shot activities and untrimmed test videos, and can benef…
UC Santa Barbara（加州大学圣巴巴拉分校）；University of Maryland（马里兰大学）
In this paper, we present a novel Single Shot multi-Span Detector for temporal activity detection in long, untrimmed videos using a simple end-to-end fully three-dimensional convolutional (Conv3D) network. Our architecture, named S3D, encodes the entire video stream and discretizes the output space of temporal activity spans into a set of default spans over different temporal locations and scales. At prediction time, S3D predicts scores for the presence of activity categories in each default span and produces temporal adjustments relative to the span location to predict the precise activity du…
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is practically able to encompass the entire label set. In this paper, we present an approach to fine-grained recognition that models activities as compositions of dynamic action signatures. This compositional approach allows us to reframe fine-grained recognition as zero-shot activity recognition, where a detector is composed "on the fly" from simple first-princip…
Paul G. Allen School of Computer Science & Engineering（保罗·G·艾伦计算机科学与工程学院）；University of Washington（华盛顿大学）
In this paper, we investigate large-scale zero-shot activity recognition by modeling the visual and linguistic attributes of action verbs. For example, the verb "salute" has several properties, such as being a light movement, a social act, and short in duration. We use these attributes as the internal mapping between visual and textual representations to reason about a previously unseen action. In contrast to much prior work that assumes access to gold standard attributes for zero-shot classes and focuses primarily on object attributes, our model uniquely learns to infer action attributes from…
Indian Institute of Technology, Delhi（德里印度理工学院）；RAeS (Royal Aeronautical Society)（皇家航空学会）
There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel action categories which are represented by few instances in the training data. We propose a novel variational inference based architectural framework (HF-AR) for few shot activity recognition. Our framework leverages volume-preserving Householder Flow to learn a flexible posterior distribution of the novel classes. This results in better performance as compar…
In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recognition network to extract the features. On the textual side, we worked with GloVe word embeddings. The zero-shot recognition results are evaluated by top-n accuracy. Then, the manifold learning ability is measured by mean Nearest Neighbor Overlap. In the end, we provide an extens…
The Pictorial Cortex: Zero-Shot Cross-Subject fMRI-to-Image Reconstruction via Compositional Latent Modeling
Institute of Science and Technology for Brain-inspired Intelligence (ISTBI), Fudan University（脑启发智能科学与技术研究院，复旦大学）；School of Data Science, Fudan University（复旦大学数据科学学院）；Fudan ISTBI–ZJNU Algorithm Centre for Brain-Inspired Intelligence, Zhejiang Normal University（复旦ISTBI-浙师大脑启发智能算法中心，浙江师范大学）；Shanghai Innovation Institute（上海创新研究院）；Nanyang Technological University（南洋理工大学）
OriginAI；Technion（以色列理工学院）；IBM Research AI（IBM研究院人工智能部门）
Classification of new class entities requires collecting and annotating hundreds or thousands of samples that is often prohibitively costly. Few-shot learning suggests learning to classify new classes using just a few examples. Only a small number of studies address the challenge of few-shot learning on spatio-temporal patterns such as videos. In this paper, we present the Temporal Aware Embedding Network (TAEN) for few-shot action recognition, that learns to represent actions, in a metric space as a trajectory, conveying both short term semantics and longer term connectivity between action pa…
We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR). Our model employs a conceptually new pipeline by which visual representations are learned in conjunction with visual-semantic associations in an end-to-end manner. The model design provides a natural mechanism for visual and semantic representations to be learned in a shared knowledge space, whereby it encourages the learned visual embedding to be discriminative and more semantically consistent. In zero-shot inference, we devise a simple semantic trans…
University of Tübingen（图宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time. The natural semantic and temporal alignment between audio and visual data in video data can be exploited to learn powerful representations that generalise to unseen classes at test time. We propose a multi-modal and Temporal Cross-attention Framework (\modelName) for audio-visual generalised zero-shot learning. Its inputs are temporally aligned audio and vis…
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos, even not seen at training time. We adopt a Transformer-based two-stage action localization architecture with class-agnostic action proposal, followed by open-vocabulary classification. We make the following contributions. First, to compensate image-text foundation models with temporal motions, we improve category-agnostic action proposal by explicitly alignin…
GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding
China Agricultural University（中国农业大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；AniEye Technology（安尼眼科技）；State Key Laboratory of Animal Nutrition and Feeding（动物营养与饲料国家重点实验室）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；University of Maryland, College Park（马里兰大学帕克分校）
Recognizing instances at different scales simultaneously is a fundamental challenge in visual detection problems. While spatial multi-scale modeling has been well studied in object detection, how to effectively apply a multi-scale architecture to temporal models for activity detection is still under-explored. In this paper, we identify three unique challenges that need to be specifically handled for temporal activity detection compared to its spatial counterpart. To address all these issues, we propose Dynamic Temporal Pyramid Network (DTPN), a new activity detection framework with a multi-sca…
We present a method to learn a joint multimodal representation space that enables recognition of unseen activities in videos. We first compare the effect of placing various constraints on the embedding space using paired text and video data. We also propose a method to improve the joint embedding space using an adversarial formulation, allowing it to benefit from unpaired text and video data. By using unpaired text data, we show the ability to learn a representation that better captures unseen activities. In addition to testing on publicly available datasets, we introduce a new, large-scale te…
Southeast University（东南大学）；Centre de Recherche en Information Biomédicale Sino-Français (CRIBs)（中法生物医学信息研究中心）；Univ Rennes（雷恩大学）；Inserm（法国国家健康与医学研究院）；LTSI - UMR1099（信号与图像处理实验室）
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation. However, further adoption of the joint models are hindered: 1) the diversity of augmentation data is reduced limiting the further enhancement of segmentation, 2) misaligned regions in weakly supervised data disturb the training process, 3) lack of label-based region constraints in few-shot situation limits the registration…
University of Bonn（波恩大学）；National University of Singapore（新加坡国立大学）
How can we teach a robot to predict what will happen next for an activity it has never seen before? We address this problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-sho…
Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. Using triplet loss, we learn a feature embedding. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances en…
Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments
Nitte (Deemed to Be University), Nitte Institute of Professional Education（尼特大学（视为大学），尼特专业教育学院）；Ballari Institute of Technology and Management（巴拉里技术与管理学院）
School of Cyber Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Engineering Research Center of Blockchain Application, Supervision and Management (Southeast University), Ministry of Education（教育部区块链应用、监督与管理工程研究中心（东南大学））；Purple Mountain Laboratories, Nanjing（紫金山实验室（南京））；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models
University of Tübingen（蒂宾根大学）；Tübingen AI Center（蒂宾根人工智能中心）；Helmholtz Munich（慕尼黑亥姆霍兹中心）；Technical University of Munich（慕尼黑工业大学）；Localyzer GmbH（Localyzer有限公司）
Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks
University of Kaiserslautern-Landau（凯泽斯劳滕-兰道大学）；Deutsches Forschungszentrum für Künstliche Intelligenz（德国人工智能研究中心）；ETH Zürich（苏黎世联邦理工学院）；Technical University of Munich（慕尼黑工业大学）
While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is capable of capturing long range spatiotemporal dependencies efficiently, contrary to existing approaches which use 3D-CNNs. Moreover, to address a common ambiguity in the existing works about classes that can be considered as previously unseen, we propose a new experimentation setup that satisfies the zero-shot learning premise for action recognition by avoidi…
Queen Mary University of London（伦敦玛丽女王大学）；City, University of London（伦敦城市大学）
Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts of annotated training samples for each class -- either in a fully-supervised setting, where action boundaries are known, or in a weakly-supervised setting, where only class labels are known for each video. In this paper, we go a step further and show that it is possible to learn to localize actions in untrimmed videos when a) only one/few trimmed examples of the target action are available at test time, and b) when …
Borealis AI；Simon Fraser University（西蒙菲莎大学）；University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（Vector人工智能研究所）
Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos -- making progress toward addressing the important, open problem of video generation in complex scenes. In particular, we introduce the task of generating human-object interaction videos in a zero-shot compositional setting, i.e., generating videos for action-object compositions that are unseen during training, having seen the target action and target object separately. This setting is particularly important for generalization in human activity video g…
On Aligning Hierarchical Standardized Embedding for Audio-visual Generalized Zero-shot Learning
Southeast University（东南大学）；The University of Hong Kong（香港大学）；Beijing Institute of Technology（北京理工大学）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（新一代人工智能技术及其跨学科应用重点实验室（东南大学），教育部）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
Improving Out-of-distribution Human Activity Recognition via IMU-Video Cross-modal Representation Learning
Department of Computer Science & Engineering University of Minnesota（计算机科学与工程系明尼苏达大学）；Department of Mechanical Engineering University of Minnesota（机械工程系明尼苏达大学）；Department of Neurosurgery University of Minnesota（神经外科系明尼苏达大学）
University of Pretoria（比勒陀利亚大学）；Malmö University（马尔默大学）
Visual Human Activity Recognition (HAR) and data fusion with other sensors can help us at tracking the behavior and activity of underground miners with little obstruction. Existing models, such as Single Shot Detector (SSD), trained on the Common Objects in Context (COCO) dataset is used in this paper to detect the current state of a miner, such as an injured miner vs a non-injured miner. Tensorflow is used for the abstraction layer of implementing machine learning algorithms, and although it uses Python to deal with nodes and tensors, the actual algorithms run on C++ libraries, providing a go…
GIST（韩国科学技术院）；UC Berkeley Vision AI Lab, AI Center, NCSOFT（加州大学伯克利分校视觉人工智能实验室、人工智能中心、NCSOFT公司）
Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries. To eliminate the annotation costs, we make a first attempt to train a natural language video localization model in zero-shot manner. Inspired by unsupervised image captioning setup, we merely require random text corpora, unlabeled video collections, and an off-the-shelf object detector to train a model. With the unpaired data, we propose to generate pseudo-supervision of candidate temporal regions and corresponding query sentences, and develop a si…
Exploiting the inner-shot and inter-shot dependencies is essential for key-shot based video summarization. Current approaches mainly devote to modeling the video as a frame sequence by recurrent neural networks. However, one potential limitation of the sequence models is that they focus on capturing local neighborhood dependencies while the high-order dependencies in long distance are not fully exploited. In general, the frames in each shot record a certain activity and vary smoothly over time, but the multi-hop relationships occur frequently among shots. In this case, both the local and globa…
Semnan University（塞姆南大学）；Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））；Universitat de Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
Sign Language Recognition (SLR) is a challenging research area in computer vision. To tackle the annotation bottleneck in SLR, we formulate the problem of Zero-Shot Sign Language Recognition (ZS-SLR) and propose a two-stream model from two input modalities: RGB and Depth videos. To benefit from the vision Transformer capabilities, we use two vision Transformer models, for human detection and visual features representation. We configure a transformer encoder-decoder architecture, as a fast and accurate human detection model, to overcome the challenges of the current human detection models. Cons…
