Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such object detectors from image to video is not trivial especially when appearance deterioration exists in videos, \emph{e.g.}, motion blur or occlusion. A valid question is how to explore temporal coherence across frames for boosting detection. In this paper, we propose to address the problem by enhancing per-frame features through aggregation of neighboring frames. Specifically, we present Single Shot Video Object Detector (SSVD) -- a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos. Technically, SSVD takes Feature Pyramid Network (FPN) as backbone network to produce multi-scale features. Unlike the existing feature aggregation methods, SSVD, on one hand, estimates the motion and aggregates the nearby features along the motion path, and on the other, hallucinates features by directly sampling features from the adjacent frames in a two-stream structure. Extensive experiments are conducted on ImageNet VID dataset, and competitive results are reported when comparing to state-of-the-art approaches. More remarkably, for $448 \times 448$ input, SSVD achieves 79.2% mAP on ImageNet VID, by processing one frame in 85 ms on an Nvidia Titan X Pascal GPU. The code is available at \url{https://github.com/ddjiajun/SSVD}.
The Hong Kong University of Science and Technology（香港科技大学）；Kuaishou Technology（快手科技）
We introduce Few-Shot Video Object Detection (FSVOD) with three contributions to real-world visual learning challenge in our highly diverse and dynamic world: 1) a large-scale video dataset FSVOD-500 comprising of 500 classes with class-balanced videos in each category for few-shot learning; 2) a novel Tube Proposal Network (TPN) to generate high-quality video tube proposals for aggregating feature representation for the target video object which can be highly dynamic; 3) a strategically improved Temporal Matching Network (TMN+) for matching representative query tube features with better discr…
The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the level of details in spatio-temporal video understanding and with it, the complexity of annotations continues to increase. Rather than performing few-shot learning with a human oracle to provide a few densely labelled support videos, we propose to automatically learn to find appropriate support videos given a query. We call this self-shot learning …
Wyze Labs, Inc.（Wyze实验室公司）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Zhejiang University（浙江大学）；University of Rochester（罗切斯特大学）
Different from static images, videos contain additional temporal and spatial information for better object detection. However, it is costly to obtain a large number of videos with bounding box annotations that are required for supervised deep learning. Although humans can easily learn to recognize new objects by watching only a few video clips, deep learning usually suffers from overfitting. This leads to an important question: how to effectively learn a video object detector from only a few labeled video clips? In this paper, we study the new problem of few-shot learning for video object dete…
Shot boundary detection in video is one of the key stages of video data processing. A new method for shot boundary detection based on several video features, such as color histograms and object boundaries, has been proposed. The developed algorithm was tested on the open BBC Planet Earth [1] and RAI [2] datasets, and the MSU CC datasets, based on videos used in the video codec comparison conducted at MSU, as well as videos from the IBM set, were also plotted. The total dataset for algorithm development and testing exceeded the known TRECVID datasets. Based on the test results, the proposed alg…
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…
Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle, fine-tuning VOS methods train a segmentation model separately on each given object mask. However, recently the VOS community has deemed such a test time optimization and its impact on the test runtime as unfeasible. To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). In contrast to most …
Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
Bytedance Inc.（字节跳动公司）；AAII, UTS（悉尼科技大学人工智能研究院）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；University of Science and Technology of China（中国科学技术大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61部门）
University of Michigan（密歇根大学）；Adobe Research（奥多比研究院）
Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models have not been adapted to video, mainly because they do not account for the time dimension but also because video frames are different from the typical images (e.g., containing motion blur, and less sharpness). In this paper, we present a fine-tuning strategy to refine these large-scale pretrained image-text models for zero-shot video understanding tasks. We show that by carefully adapting t…
Pontificia Universidad Católica de Chile（智利天主教大学）；Samsung AI Centre Cambridge（三星人工智能中心剑桥）；Stanford University（斯坦福大学）；KU Leuven（鲁汶大学）；Facebook AI（Facebook 人工智能）
Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve learning under low data regimes. However, most works have largely ignored that videos are often accompanied by rich textual descriptions that can also be an essential source of information to handle few-shot recognition cases. In this paper, we propose to leverage these human-provided textual descriptions as privileged information when training a few-shot video classification model. Specifically, we formulate a text-b…
National Key Lab for Novel Software Technology（新型软件技术国家重点实验室）；Nanjing University（南京大学）
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos in such a setting. In this paper, we propose Temporal Alignment Prediction (TAP) based on sequence similarity learning for few-shot video classification. In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function. Besides, the …
ETH Zurich（苏黎世联邦理工学院）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Oxford（牛津大学）；Facebook（脸书公司）；Dartmouth College（达特茅斯学院）；University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Few-shot learning aims to recognize novel classes from a few examples. Although significant progress has been made in the image domain, few-shot video classification is relatively unexplored. We argue that previous methods underestimate the importance of video feature learning and propose to learn spatiotemporal features using a 3D CNN. Proposing a two-stage approach that learns video features on base classes followed by fine-tuning the classifiers on novel classes, we show that this simple baseline approach outperforms prior few-shot video classification methods by over 20 points on existing …
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from training samples with missing classes. The task is an extension of conditional data generation. The key idea is to learn disentangled representations in the latent space of a GAN. To realize this objective, we base our model on the motion and content decomposed GAN and conditional GAN for image generation. We build the model to find better-disentangled representations and to g…
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel …
We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to achieve the appearance similarity score between the videos, while utilizing temporal order-preserving priors for obtaining the temporal similarity score between the videos. Moreover, we introduce a few-shot video classification framework that leverages the above appearance and temporal similarity scores across multiple steps, namely prototype-based training and…
National University of Singapore（新加坡国立大学）；Tencent PCG（腾讯平台与内容事业群）
To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting$\unicode{x2014}$One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple…
We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Unlike zero-shot image captioning methods, our work considers the entire sentence at once. This is achieved by optimizing, during the generation process, part of the prompt from scratch, by modifying the representation of all other tokens in the prompt, and by repeating the process iteratively, …
Tencent AI Lab（腾讯人工智能实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）
Action recognition in surveillance video makes our life safer by detecting the criminal events or predicting violent emergencies. However, efficient action recognition is not free of difficulty. First, there are so many action classes in daily life that we cannot pre-define all possible action classes beforehand. Moreover, it is very hard to collect real-word videos for certain particular actions such as steal and street fight due to legal restrictions and privacy protection. These challenges make existing data-driven recognition methods insufficient to attain desired performance. Zero-shot le…
Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models
School of Electrical and Information Engineering, Tianjin University（电子信息工程学院，天津大学）；Computer Vision and Pattern Recognition Laboratory, School of Engineering Science, Lappeenranta-Lahti University of Technology LUT（计算机视觉与模式识别实验室，工程科学学院，拉佩兰塔-拉赫蒂技术大学LUT）
Corning Inc.（康宁公司）；University of Rochester（罗切斯特大学）
Video anomaly detection aims to identify abnormal events that occurred in videos. Since anomalous events are relatively rare, it is not feasible to collect a balanced dataset and train a binary classifier to solve the task. Thus, most previous approaches learn only from normal videos using unsupervised or semi-supervised methods. Obviously, they are limited in capturing and utilizing discriminative abnormal characteristics, which leads to compromised anomaly detection performance. In this paper, to address this issue, we propose a new learning paradigm by making full use of both normal and abn…
Detection of video shot transition is a crucial pre-processing step in video analysis. Previous studies are restricted on detecting sudden content changes between frames through similarity measurement and multi-scale operations are widely utilized to deal with transitions of various lengths. However, localization of gradual transitions are still under-explored due to the high visual similarity between adjacent frames. Cut shot transitions are abrupt semantic breaks while gradual shot transitions contain low-level spatial-temporal patterns caused by video effects in addition to the gradual sema…
This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally…
VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；Tencent AI Lab（腾讯AI实验室）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Federal Institute of Paraná（巴拉那联邦学院）；Federal University of Paraná（巴拉那联邦大学）
Zero-Shot Action Recognition has attracted attention in the last years and many approaches have been proposed for recognition of objects, events and actions in images and videos. There is a demand for methods that can classify instances from classes that are not present in the training of models, especially in the complex problem of automatic video understanding, since collecting, annotating and labeling videos are difficult and laborious tasks. We have identified that there are many methods available in the literature, however, it is difficult to categorize which techniques can be considered …
This paper presents a novel approach for video shot boundary detection. The proposed approach is based on split and merge concept. A fisher linear discriminant criterion is used to guide the process of both splitting and merging. For the purpose of capturing the between class and within class scatter we employ 2D2 FLD method which works on texture feature of regions in each frame of a video. Further to reduce the complexity of the process we propose to employ spectral clustering to group related regions together to a single there by achieving reduction in dimension. The proposed method is expe…
Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
Inria（法国国家信息与自动化研究所）；Univ Rennes（雷恩大学）；CNRS（法国国家科学研究中心）；IRISA（法国雷恩信息与自动化系统研究所）；Institute of Advanced Research in Artificial Intelligence (IARAI)（高级人工智能研究所（IARAI））
The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on learning effective representations, and heavily rely on the ImageNet pre-training, which might be unreasonable for the few-shot recognition setting due to semantics overlap. In this paper, we aim to present an in-depth study on few-shot video classification by making three contributions. First, we perform a consistent comparative study on the existing metric…
Recognizing the phases of a laparoscopic surgery (LS) operation form its video constitutes a fundamental step for efficient content representation, indexing and retrieval in surgical video databases. In the literature, most techniques focus on phase segmentation of the entire LS video using hand-crafted visual features, instrument usage signals, and recently convolutional neural networks (CNNs). In this paper we address the problem of phase recognition of short video shots (10s) of the operation, without utilizing information about the preceding/forthcoming video frames, their phase labels or …
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
The 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）；Kling Team, Kuaishou Technology（Kling团队，快手科技）；Tsinghua University（清华大学）；Sun Yat-sen University（中山大学）
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；University of Liberal Arts Bangladesh（孟加拉国文科大学）；University of Toronto（多伦多大学）
In the Internet, ubiquitous presence of redundant, unedited, raw videos has made video summarization an important problem. Traditional methods of video summarization employ a heuristic set of hand-crafted features, which in many cases fail to capture subtle abstraction of a scene. This paper presents a deep learning method that maps the context of a video to the importance of a scene similar to that is perceived by humans. In particular, a convolutional neural network (CNN)-based architecture is proposed to mimic the frame-level shot importance for user-oriented video summarization. The weight…
Recently, removing objects from videos and filling in the erased regions using deep video inpainting (VI) algorithms has attracted considerable attention. Usually, a video sequence and object segmentation masks for all frames are required as the input for this task. However, in real-world applications, providing segmentation masks for all frames is quite difficult and inefficient. Therefore, we deal with VI in a one-shot manner, which only takes the initial frame's object mask as its input. Although we can achieve that using naive combinations of video object segmentation (VOS) and VI methods,…
Zhejiang University（浙江大学）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Hikvision Research Institute（海康威视研究院）；Northwestern Polytechnical University（西北工业大学）；Shanghai AI Laboratory（上海人工智能实验室）
Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner. One major challenge of end-to-end one-shot video grounding is the existence of videos frames that are …
