Most methods tackle zero-shot video classification by aligning visual-semantic representations within seen classes, which limits generalization to unseen classes. To enhance model generalizability, this paper presents an end-to-end framework that preserves alignment and uniformity properties for representations on both seen and unseen classes. Specifically, we formulate a supervised contrastive loss to simultaneously align visual-semantic features (i.e., alignment) and encourage the learned features to distribute uniformly (i.e., uniformity). Unlike existing methods that only consider the alignment, we propose uniformity to preserve maximal-info of existing features, which improves the probability that unobserved features fall around observed data. Further, we synthesize features of unseen classes by proposing a class generator that interpolates and extrapolates the features of seen classes. Besides, we introduce two metrics, closeness and dispersion, to quantify the two properties and serve as new measurements of model generalizability. Experiments show that our method significantly outperforms SoTA by relative improvements of 28.1% on UCF101 and 27.0% on HMDB51. Code is available.
Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first randomly select temporal regions, each of which contains multiple clips, from one video as pseudo actions and then paste them onto different temporal positions of the other two videos. The pretext task is to align the features of pasted pseudo action regions from two synthetic videos and maximize the agreement between them. Compared to the existing unsupervised video representation learning approaches, our PAL adapts better to downstream TAL tasks by introducing a temporal equivariant contrastive learning paradigm in a temporally dense and scale-aware manner. Extensive experiments show that PAL can utilize large-scale unlabeled video data to significantly boost the performance of existing TAL methods. Our codes and models will be made publicly available at https://github.com/zhang-can/UP-TAL.
Video-based movie genre classification has garnered considerable attention due to its various applications in recommendation systems. Prior work has typically addressed this task by adapting models from traditional video classification tasks, such as action recognition or event detection. However, these models often neglect language elements (e.g., narrations or conversations) present in videos, which can implicitly convey high-level semantics of movie genres, like storylines or background context. Additionally, existing approaches are primarily designed to encode the entire content of the input video, leading to inefficiencies in predicting movie genres. Movie genre prediction may require only a few shots to accurately determine the genres, rendering a comprehensive understanding of the entire video unnecessary. To address these challenges, we propose a Movie genre Classification method based on Language augmentatIon and shot samPling (Movie-CLIP). Movie-CLIP mainly consists of two parts: a language augmentation module to recognize language elements from the input audio, and a shot sampling module to select representative shots from the entire video. We evaluate our method on MovieNet and Condensed Movies datasets, achieving approximate 6-9% improvement in mean Average Precision (mAP) over the baselines. We also generalize Movie-CLIP to the scene boundary detection task, achieving 1.1% improvement in Average Precision (AP) over the state-of-the-art. We release our implementation at github.com/Zhongping-Zhang/Movie-CLIP.
Automating video-based data and machine learning pipelines poses several challenges including metadata generation for efficient storage and retrieval and isolation of key-frames for scene understanding tasks. In this work, we present two semi-supervised approaches that automate this process of manual frame sifting in video streams by automatically classifying scenes for content and filtering frames for fine-tuning scene understanding tasks. The first rule-based method starts from a pre-trained object detector and it assigns scene type, uncertainty and lighting categories to each frame based on probability distributions of foreground objects. Next, frames with the highest uncertainty and structural dissimilarity are isolated as key-frames. The second method relies on the simCLR model for frame encoding followed by label-spreading from 20% of frame samples to label the remaining frames for scene and lighting categories. Also, clustering the video frames in the encoded feature space further isolates key-frames at cluster boundaries. The proposed methods achieve 64-93% accuracy for automated scene categorization for outdoor image videos from public domain datasets of JAAD and KITTI. Also, less than 10% of all input frames can be filtered as key-frames that can then be sent for annotation and fine tuning of machine vision algorithms. Thus, the proposed framework can be scaled to additional video data streams for automated training of perception-driven systems with minimal training images.
Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.
Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\textit{R}$-$\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\sim$ 2.4$\times$ while achieving over 90$\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.
Temporal Reasoning is one important functionality for vision intelligence. In computer vision research community, temporal reasoning is usually studied in the form of video classification, for which many state-of-the-art Neural Network structures and dataset benchmarks are proposed in recent years, especially 3D CNNs and Kinetics. However, some recent works found that current video classification benchmarks contain strong biases towards static features, thus cannot accurately reflect the temporal modeling ability. New video classification benchmarks aiming to eliminate static biases are proposed, with experiments on these new benchmarks showing that the current clip-based 3D CNNs are outperformed by RNN structures and recent video transformers. In this paper, we find that 3D CNNs and their efficient depthwise variants, when video-level sampling strategy is used, are actually able to beat RNNs and recent vision transformers by significant margins on static-unbiased temporal reasoning benchmarks. Further, we propose Temporal Fully Connected Block (TFC Block), an efficient and effective component, which approximates fully connected layers along temporal dimension to obtain video-level receptive field, enhancing the spatiotemporal reasoning ability. With TFC blocks inserted into Video-level 3D CNNs (V3D), our proposed TFCNets establish new state-of-the-art results on synthetic temporal reasoning benchmark, CATER, and real world static-unbiased dataset, Diving48, surpassing all previous methods.
Object detection serves as a significant step in improving performance of complex downstream computer vision tasks. It has been extensively studied for many years now and current state-of-the-art 2D object detection techniques proffer superlative results even in complex images. In this chapter, we discuss the geometry-based pioneering works in object detection, followed by the recent breakthroughs that employ deep learning. Some of these use a monolithic architecture that takes a RGB image as input and passes it to a feed-forward ConvNet or vision Transformer. These methods, thereby predict class-probability and bounding-box coordinates, all in a single unified pipeline. Two-stage architectures on the other hand, first generate region proposals and then feed it to a CNN to extract features and predict object category and bounding-box. We also elaborate upon the applications of object detection in video event recognition, to achieve better fine-grained video classification performance. Further, we highlight recent datasets for 2D object detection both in images and videos, and present a comparative performance summary of various state-of-the-art object detection techniques.
This paper introduces a new challenge and datasets to foster research toward designing systems that can understand medical videos and provide visual answers to natural language questions. We believe medical videos may provide the best possible answers to many first aids, medical emergency, and medical education questions. Toward this, we created the MedVidCL and MedVidQA datasets and introduce the tasks of Medical Video Classification (MVC) and Medical Visual Answer Localization (MVAL), two tasks that focus on cross-modal (medical language and medical video) understanding. The proposed tasks and datasets have the potential to support the development of sophisticated downstream applications that can benefit the public and medical practitioners. Our datasets consist of 6,117 annotated videos for the MVC task and 3,010 annotated questions and answers timestamps from 899 videos for the MVAL task. These datasets have been verified and corrected by medical informatics experts. We have also benchmarked each task with the created MedVidCL and MedVidQA datasets and proposed the multimodal learning methods that set competitive baselines for future research.
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to several minutes. Accurately categorizing these activities requires not only recognizing the individual steps that compose the task but also capturing their temporal dependencies. This problem is dramatically different from traditional action classification, where models are typically optimized on videos that span only a few seconds and that are manually trimmed to contain simple atomic actions. While step annotations could enable the training of models to recognize the individual steps of procedural activities, existing large-scale datasets in this area do not include such segment labels due to the prohibitive cost of manually annotating temporal boundaries in long videos. To address this issue, we propose to automatically identify steps in instructional videos by leveraging the distant supervision of a textual knowledge base (wikiHow) that includes detailed descriptions of the steps needed for the execution of a wide variety of complex activities. Our method uses a language model to match noisy, automatically-transcribed speech from the video to step descriptions in the knowledge base. We demonstrate that video models trained to recognize these automatically-labeled steps (without manual supervision) yield a representation that achieves superior generalization performance on four downstream tasks: recognition of procedural activities, step classification, step forecasting and egocentric video classification.
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters in the temporal dimension to turn them into 3D networks, or using optical flow, etc.), which increases computation cost. Instead, we propose a novel sampling strategy, where we re-order the channels of the input video, to capture short-term frame-to-frame changes. We observe that without bells and whistles, the proposed sampling strategy improves performance on multiple architectures (e.g. TSN, TRN, TSM, and MVFNet) and datasets (CATER, Something-Something-V1 and V2), up to 24% over the baseline of using the standard video input. In addition, our sampling strategies do not require training from scratch and do not increase the computational cost of training and testing. Given the generality of the results and the flexibility of the approach, we hope this can be widely useful to the video understanding community. Code is available on our website: https://github.com/kiyoon/channel_sampling.
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our UniFormer blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks, e.g., it obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Sth-Sth V1/V2 video classification, 53.8 box AP and 46.4 mask AP on COCO object detection, 50.8 mIoU on ADE20K semantic segmentation, and 77.4 AP on COCO pose estimation. We further build an efficient UniFormer with 2-4x higher throughput. Code is available at https://github.com/Sense-X/UniFormer.
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep models. Considering that the annotation of large-scale datasets is time-consuming, we propose a multimodal self-supervised learning framework to obtain semantic representations of videos, which benefits the video summarization task. Specifically, the self-supervised learning is conducted by exploring the semantic consistency between the videos and text in both coarse-grained and fine-grained fashions, as well as recovering masked frames in the videos. The multimodal framework is trained on a newly-collected dataset that consists of video-text pairs. Additionally, we introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. Extensive experiments have proved the effectiveness and superiority of our method in rank correlation coefficients and F-score.
In recent years, many works have addressed the problem of finding never-seen-before anomalies in videos. Yet, most work has been focused on detecting anomalous frames in surveillance videos taken from security cameras. Meanwhile, the task of anomaly detection (AD) in videos exhibiting anomalous mechanical behavior, has been mostly overlooked. Anomaly detection in such videos is both of academic and practical interest, as they may enable automatic detection of malfunctions in many manufacturing, maintenance, and real-life settings. To assess the potential of the different approaches to detect such anomalies, we evaluate two simple baseline approaches: (i) Temporal-pooled image AD techniques. (ii) Density estimation of videos represented with features pretrained for video-classification. Development of such methods calls for new benchmarks to allow evaluation of different possible approaches. We introduce the Physical Anomalous Trajectory or Motion (PHANTOM) dataset, which contains six different video classes. Each class consists of normal and anomalous videos. The classes differ in the presented phenomena, the normal class variability, and the kind of anomalies in the videos. We also suggest an even harder benchmark where anomalous activities should be spotted on highly variable scenes.
In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance especially with recent transformer-based video architectures. While recently many works aim to design more advanced transformer architectures for action recognition, less effort has been made on how to train video transformers. In this work, we explore several training paradigms and present two findings. First, video transformers benefit from joint training on diverse video datasets and label spaces (e.g., Kinetics is appearance-focused while SomethingSomething is motion-focused). Second, by further co-training with images (as single-frame videos), the video transformers learn even better video representations. We term this approach as Co-training Videos and Images for Action Recognition (CoVeR). In particular, when pretrained on ImageNet-21K based on the TimeSFormer architecture, CoVeR improves Kinetics-400 Top-1 Accuracy by 2.4%, Kinetics-600 by 2.3%, and SomethingSomething-v2 by 2.3%. When pretrained on larger-scale image datasets following previous state-of-the-art, CoVeR achieves best results on Kinetics-400 (87.2%), Kinetics-600 (87.9%), Kinetics-700 (79.8%), SomethingSomething-v2 (70.9%), and Moments-in-Time (46.1%), with a simple spatio-temporal video transformer.
We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal representation,e.g., using 2D CNN, 3D CNN, and Video Transformer. Then, to make the most of such representations, we use self- and cross-attention models to highlight the critical spatio-temporal region to increase the inter-class variations and decrease the intra-class variations. Last, MASTAF applies a lightweight fusion network and a nearest neighbor classifier to classify each query video. We demonstrate that MASTAF improves the state-of-the-art performance on three few-shot video classification benchmarks(UCF101, HMDB51, and Something-Something-V2), e.g., by up to 91.6%, 69.5%, and 60.7% for five-way one-shot video classification, respectively.
Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods typically randomly sample video clips for learning, which results in an imperfect supervisory signal. In this work, we propose PreViTS, an SSL framework that utilizes an unsupervised tracking signal for selecting clips containing the same object, which helps better utilize temporal transformations of objects. PreViTS further uses the tracking signal to spatially constrain the frame regions to learn from and trains the model to locate meaningful objects by providing supervision on Grad-CAM attention maps. To evaluate our approach, we train a momentum contrastive (MoCo) encoder on VGG-Sound and Kinetics-400 datasets with PreViTS. Training with PreViTS outperforms representations learnt by contrastive strategy alone on video downstream tasks, obtaining state-of-the-art performance on action classification. PreViTS helps learn feature representations that are more robust to changes in background and context, as seen by experiments on datasets with background changes. Learning from large-scale videos with PreViTS could lead to more accurate and robust visual feature representations.
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bells-and-whistles, MViTv2 has state-of-the-art performance in 3 domains: 88.8% accuracy on ImageNet classification, 58.7 boxAP on COCO object detection as well as 86.1% on Kinetics-400 video classification. Code and models are available at https://github.com/facebookresearch/mvit.
While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the number of tokens in the network, there is no setting that is optimal for all input images. In this work, we therefore introduce a differentiable parameter-free Adaptive Token Sampler (ATS) module, which can be plugged into any existing vision transformer architecture. ATS empowers vision transformers by scoring and adaptively sampling significant tokens. As a result, the number of tokens is not constant anymore and varies for each input image. By integrating ATS as an additional layer within the current transformer blocks, we can convert them into much more efficient vision transformers with an adaptive number of tokens. Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training. Moreover, due to its differentiable design, one can also train a vision transformer equipped with ATS. We evaluate the efficiency of our module in both image and video classification tasks by adding it to multiple SOTA vision transformers. Our proposed module improves the SOTA by reducing their computational costs (GFLOPs) by 2X, while preserving their accuracy on the ImageNet, Kinetics-400, and Kinetics-600 datasets.
Recently, MLP-Like networks have been revived for image recognition. However, whether it is possible to build a generic MLP-Like architecture on video domain has not been explored, due to complex spatial-temporal modeling with large computation burden. To fill this gap, we present an efficient self-attention free backbone, namely MorphMLP, which flexibly leverages the concise Fully-Connected (FC) layer for video representation learning. Specifically, a MorphMLP block consists of two key layers in sequence, i.e., MorphFC_s and MorphFC_t, for spatial and temporal modeling respectively. MorphFC_s can effectively capture core semantics in each frame, by progressive token interaction along both height and width dimensions. Alternatively, MorphFC_t can adaptively learn long-term dependency over frames, by temporal token aggregation on each spatial location. With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance. Finally, we evaluate our MorphMLP on a number of popular video benchmarks. Compared with the recent state-of-the-art models, MorphMLP significantly reduces computation but with better accuracy, e.g., MorphMLP-S only uses 50% GFLOPs of VideoSwin-T but achieves 0.9% top-1 improvement on Kinetics400, under ImageNet1K pretraining. MorphMLP-B only uses 43% GFLOPs of MViT-B but achieves 2.4% top-1 improvement on SSV2, even though MorphMLP-B is pretrained on ImageNet1K while MViT-B is pretrained on Kinetics400. Moreover, our method adapted to the image domain outperforms previous SOTA MLP-Like architectures. Code is available at https://github.com/MTLab/MorphMLP.