The traffic video data has become a critical factor in confining the state of traffic congestion due to the recent advancements in computer vision. This work proposes a unique technique for traffic video classification using a color-coding scheme before training the traffic data in a Deep convolutional neural network. At first, the video data is transformed into an imagery data set; then, the vehicle detection is performed using the You Only Look Once algorithm. A color-coded scheme has been adopted to transform the imagery dataset into a binary image dataset. These binary images are fed to a Deep Convolutional Neural Network. Using the UCSD dataset, we have obtained a classification accuracy of 98.2%.
https://arxiv.org/abs/2209.07943
Recently vision transformers have been shown to be competitive with convolution-based methods (CNNs) broadly across multiple vision tasks. The less restrictive inductive bias of transformers endows greater representational capacity in comparison with CNNs. However, in the image classification setting this flexibility comes with a trade-off with respect to sample efficiency, where transformers require ImageNet-scale training. This notion has carried over to video where transformers have not yet been explored for video classification in the low-labeled or semi-supervised settings. Our work empirically explores the low data regime for video classification and discovers that, surprisingly, transformers perform extremely well in the low-labeled video setting compared to CNNs. We specifically evaluate video vision transformers across two contrasting video datasets (Kinetics-400 and SomethingSomething-V2) and perform thorough analysis and ablation studies to explain this observation using the predominant features of video transformer architectures. We even show that using just the labeled data, transformers significantly outperform complex semi-supervised CNN methods that leverage large-scale unlabeled data as well. Our experiments inform our recommendation that semi-supervised learning video work should consider the use of video transformers in the future.
https://arxiv.org/abs/2209.07474
Unmanned Aerial Vehicle (UAV) has gained significant traction in the recent years, particularly the context of surveillance. However, video datasets that capture violent and non-violent human activity from aerial point-of-view is scarce. To address this issue, we propose a novel, baseline simulator which is capable of generating sequences of photo-realistic synthetic images of crowds engaging in various activities that can be categorized as violent or non-violent. The crowd groups are annotated with bounding boxes that are automatically computed using semantic segmentation. Our simulator is capable of generating large, randomized urban environments and is able to maintain an average of 25 frames per second on a mid-range computer with 150 concurrent crowd agents interacting with each other. We also show that when synthetic data from the proposed simulator is augmented with real world data, binary video classification accuracy is improved by 5% on average across two different models.
https://arxiv.org/abs/2208.06702
Contrastive learning has shown great potential in video representation learning. However, existing approaches fail to sufficiently exploit short-term motion dynamics, which are crucial to various down-stream video understanding tasks. In this paper, we propose Motion Sensitive Contrastive Learning (MSCL) that injects the motion information captured by optical flows into RGB frames to strengthen feature learning. To achieve this, in addition to clip-level global contrastive learning, we develop Local Motion Contrastive Learning (LMCL) with frame-level contrastive objectives across the two modalities. Moreover, we introduce Flow Rotation Augmentation (FRA) to generate extra motion-shuffled negative samples and Motion Differential Sampling (MDS) to accurately screen training samples. Extensive experiments on standard benchmarks validate the effectiveness of the proposed method. With the commonly-used 3D ResNet-18 as the backbone, we achieve the top-1 accuracies of 91.5\% on UCF101 and 50.3\% on Something-Something v2 for video classification, and a 65.6\% Top-1 Recall on UCF101 for video retrieval, notably improving the state-of-the-art.
https://arxiv.org/abs/2208.06105
Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource intensive and suffer from data inefficiencies. Long form video understanding tasks amplify data and memory efficiency problems in transformers making current approaches unfeasible to implement on data or memory restricted domains. This paper introduces an efficient Spatio-Temporal Attention Network (STAN) which uses a two-stream transformer architecture to model dependencies between static image features and temporal contextual features. Our proposed approach can classify videos up to two minutes in length on a single GPU, is data efficient, and achieves SOTA performance on several long video understanding tasks.
https://arxiv.org/abs/2208.01753
This paper proposes a method for visually explaining the decision-making process of 3D convolutional neural networks (CNN) with a temporal extension of occlusion sensitivity analysis. The key idea here is to occlude a specific volume of data by a 3D mask in an input 3D temporal-spatial data space and then measure the change degree in the output score. The occluded volume data that produces a larger change degree is regarded as a more critical element for classification. However, while the occlusion sensitivity analysis is commonly used to analyze single image classification, it is not so straightforward to apply this idea to video classification as a simple fixed cuboid cannot deal with the motions. To this end, we adapt the shape of a 3D occlusion mask to complicated motions of target objects. Our flexible mask adaptation is performed by considering the temporal continuity and spatial co-occurrence of the optical flows extracted from the input video data. We further propose to approximate our method by using the first-order partial derivative of the score with respect to an input image to reduce its computational cost. We demonstrate the effectiveness of our method through various and extensive comparisons with the conventional methods in terms of the deletion/insertion metric and the pointing metric on the UCF-101. The code is available at: this https URL.
https://arxiv.org/abs/2207.12859
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging. In this work, we release yet another sports video dataset $\textbf{P$^2$A}$ for $\underline{P}$ing $\underline{P}$ong-$\underline{A}$ction detection, which consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads. We work with a crew of table tennis professionals and referees to obtain fine-grained action labels (in 14 classes) for every ping-pong action that appeared in the dataset and formulate two sets of action detection problems - action localization and action recognition. We evaluate a number of commonly-seen action recognition (e.g., TSM, TSN, Video SwinTransformer, and Slowfast) and action localization models (e.g., BSN, BSN++, BMN, TCANet), using $\textbf{P$^2$A}$ for both problems, under various settings. These models can only achieve 48% area under the AR-AN curve for localization and 82% top-one accuracy for recognition since the ping-pong actions are dense with fast-moving subjects but broadcasting videos are with only 25 FPS. The results confirm that $\textbf{P$^2$A}$ is still a challenging task and can be used as a benchmark for action detection from videos.
https://arxiv.org/abs/2207.12730
In videos, the human's actions are of three-dimensional (3D) signals. These videos investigate the spatiotemporal knowledge of human behavior. The promising ability is investigated using 3D convolution neural networks (CNNs). The 3D CNNs have not yet achieved high output for their well-established two-dimensional (2D) equivalents in still photographs. Board 3D Convolutional Memory and Spatiotemporal fusion face training difficulty preventing 3D CNN from accomplishing remarkable evaluation. In this paper, we implement Hybrid Deep Learning Architecture that combines STIP and 3D CNN features to enhance the performance of 3D videos effectively. After implementation, the more detailed and deeper charting for training in each circle of space-time fusion. The training model further enhances the results after handling complicated evaluations of models. The video classification model is used in this implemented model. Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning is introduced to further understand spacetime association in human endeavors. In the implementation of the result, the well-known dataset, i.e., UCF101 to, evaluates the performance of the proposed hybrid technique. The results beat the proposed hybrid technique that substantially beats the initial 3D CNNs. The results are compared with state-of-the-art frameworks from literature for action recognition on UCF101 with an accuracy of 95%.
https://arxiv.org/abs/2207.11504
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representation induced by the two learning paradigms is similar. We investigate this under the lens of adversarial robustness. Our analytical treatment of the problem reveals intrinsic higher sensitivity of CSL over supervised learning. It identifies the uniform distribution of data representation over a unit hypersphere in the CSL representation space as the key contributor to this phenomenon. We establish that this increases model sensitivity to input perturbations in the presence of false negatives in the training data. Our finding is supported by extensive experiments for image and video classification using adversarial perturbations and other input corruptions. Building on the insights, we devise strategies that are simple, yet effective in improving model robustness with CSL training. We demonstrate up to 68% reduction in the performance gap between adversarially attacked CSL and its supervised counterpart. Finally, we contribute to robust CSL paradigm by incorporating our findings in adversarial self-supervised learning. We demonstrate an average gain of about 5% over two different state-of-the-art methods in this domain.
https://arxiv.org/abs/2207.10862
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 testing as well as inductive and transductive prototype refinement. To the best of our knowledge, our work is the first to explore transductive few-shot video classification. Extensive experiments on both Kinetics and Something-Something V2 datasets show that both appearance and temporal alignments are crucial for datasets with temporal order sensitivity such as Something-Something V2. Our approach achieves similar or better results than previous methods on both datasets. Our code is available at this https URL.
https://arxiv.org/abs/2207.10785
We present a new benchmark dataset, Sapsucker Woods 60 (SSW60), for advancing research on audiovisual fine-grained categorization. While our community has made great strides in fine-grained visual categorization on images, the counterparts in audio and video fine-grained categorization are relatively unexplored. To encourage advancements in this space, we have carefully constructed the SSW60 dataset to enable researchers to experiment with classifying the same set of categories in three different modalities: images, audio, and video. The dataset covers 60 species of birds and is comprised of images from existing datasets, and brand new, expert-curated audio and video datasets. We thoroughly benchmark audiovisual classification performance and modality fusion experiments through the use of state-of-the-art transformer methods. Our findings show that performance of audiovisual fusion methods is better than using exclusively image or audio based methods for the task of video classification. We also present interesting modality transfer experiments, enabled by the unique construction of SSW60 to encompass three different modalities. We hope the SSW60 dataset and accompanying baselines spur research in this fascinating area.
https://arxiv.org/abs/2207.10664
It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video recognition methods typically preview videos and focus on salient parts to reduce computation costs. Most existing works focus on complex networks learning with video classification based objectives. Taking all frames as positive samples, few of them pay attention to the discrimination between positive samples (salient frames) and negative samples (non-salient frames) in supervisions. To fill this gap, in this paper, we propose a novel Non-saliency Suppression Network (NSNet), which effectively suppresses the responses of non-salient frames. Specifically, on the frame level, effective pseudo labels that can distinguish between salient and non-salient frames are generated to guide the frame saliency learning. On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations. Saliency measurements from both two levels are combined for exploitation of multi-granularity complementary information. Extensive experiments conducted on four well-known benchmarks verify our NSNet not only achieves the state-of-the-art accuracy-efficiency trade-off but also present a significantly faster (2.4~4.3x) practical inference speed than state-of-the-art methods. Our project page is at this https URL .
https://arxiv.org/abs/2207.10388
Clustering is a ubiquitous tool in unsupervised learning. Most of the existing self-supervised representation learning methods typically cluster samples based on visually dominant features. While this works well for image-based self-supervision, it often fails for videos, which require understanding motion rather than focusing on background. Using optical flow as complementary information to RGB can alleviate this problem. However, we observe that a naive combination of the two views does not provide meaningful gains. In this paper, we propose a principled way to combine two views. Specifically, we propose a novel clustering strategy where we use the initial cluster assignment of each view as prior to guide the final cluster assignment of the other view. This idea will enforce similar cluster structures for both views, and the formed clusters will be semantically abstract and robust to noisy inputs coming from each individual view. Additionally, we propose a novel regularization strategy to address the feature collapse problem, which is common in cluster-based self-supervised learning methods. Our extensive evaluation shows the effectiveness of our learned representations on downstream tasks, e.g., video retrieval and action recognition. Specifically, we outperform the state of the art by 7% on UCF and 4% on HMDB for video retrieval, and 5% on UCF and 6% on HMDB for video classification
https://arxiv.org/abs/2207.10158
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 visual features that are obtained from pre-trained networks. Encouraging the framework to focus on cross-modal correspondence across time instead of self-attention within the modalities boosts the performance significantly. We show that our proposed framework that ingests temporal features yields state-of-the-art performance on the \ucf, \vgg, and \activity benchmarks for (generalised) zero-shot learning. Code for reproducing all results is available at \url{this https URL}.
https://arxiv.org/abs/2207.09966
Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that naturally exist in video. We present \textbf{MOV}, a simple yet effective method for \textbf{M}ultimodal \textbf{O}pen-\textbf{V}ocabulary video classification. In MOV, we directly use the vision encoder from pre-trained VLMs with minimal modifications to encode video, optical flow and audio spectrogram. We design a cross-modal fusion mechanism to aggregate complimentary multimodal information. Experiments on Kinetics-700 and VGGSound show that introducing flow or audio modality brings large performance gains over the pre-trained VLM and existing methods. Specifically, MOV greatly improves the accuracy on base classes, while generalizes better on novel classes. MOV achieves state-of-the-art results on UCF and HMDB zero-shot video classification benchmarks, significantly outperforming both traditional zero-shot methods and recent methods based on VLMs. Code and models will be released.
https://arxiv.org/abs/2207.07646
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes $T$ times longer sequence than the latter under the current attention of quadratic complexity $(T^2N^2)$. The existing works treat the temporal axis as a simple extension of spatial axes, focusing on shortening the spatio-temporal sequence by either generic pooling or local windowing without utilizing temporal redundancy. However, videos naturally contain redundant information between neighboring frames; thereby, we could potentially suppress attention on visually similar frames in a dilated manner. Based on this hypothesis, we propose the LAPS, a long-term ``\textbf{\textit{Leap Attention}}'' (LA), short-term ``\textbf{\textit{Periodic Shift}}'' (\textit{P}-Shift) module for video transformers, with $(2TN^2)$ complexity. Specifically, the ``LA'' groups long-term frames into pairs, then refactors each discrete pair via attention. The ``\textit{P}-Shift'' exchanges features between temporal neighbors to confront the loss of short-term dynamics. By replacing a vanilla 2D attention with the LAPS, we could adapt a static transformer into a video one, with zero extra parameters and neglectable computation overhead ($\sim$2.6\%). Experiments on the standard Kinetics-400 benchmark demonstrate that our LAPS transformer could achieve competitive performances in terms of accuracy, FLOPs, and Params among CNN and transformer SOTAs. We open-source our project in \sloppy \href{this https URL}{\textit{\color{magenta}{this https URL}}} .
https://arxiv.org/abs/2207.05526
Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on ``downstream'' tasks such as action localisation, which are smaller due to their finer-grained annotations. In this paper, we question this approach, and propose co-finetuning -- simultaneously training a single model on multiple ``upstream'' and ``downstream'' tasks. We demonstrate that co-finetuning outperforms traditional transfer learning when using the same total amount of data, and also show how we can easily extend our approach to multiple ``upstream'' datasets to further improve performance. In particular, co-finetuning significantly improves the performance on rare classes in our downstream task, as it has a regularising effect, and enables the network to learn feature representations that transfer between different datasets. Finally, we observe how co-finetuning with public, video classification datasets, we are able to achieve state-of-the-art results for spatio-temporal action localisation on the challenging AVA and AVA-Kinetics datasets, outperforming recent works which develop intricate models.
https://arxiv.org/abs/2207.03807
We introduce DAiSEE, the first multi-label video classification dataset comprising of 9068 video snippets captured from 112 users for recognizing the user affective states of boredom, confusion, engagement, and frustration in the wild. The dataset has four levels of labels namely - very low, low, high, and very high for each of the affective states, which are crowd annotated and correlated with a gold standard annotation created using a team of expert psychologists. We have also established benchmark results on this dataset using state-of-the-art video classification methods that are available today. We believe that DAiSEE will provide the research community with challenges in feature extraction, context-based inference, and development of suitable machine learning methods for related tasks, thus providing a springboard for further research. The dataset is available for download at this https URL.
https://arxiv.org/abs/1609.01885
Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a designated local region. Patch attacks can be highly effective in a variety of tasks and physically realizable via attachment (e.g. a sticker) to the real-world objects. Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images. We exploit this property and present PatchZero, a task-agnostic defense against white-box adversarial patches. Specifically, our defense detects the adversarial pixels and "zeros out" the patch region by repainting with mean pixel values. We formulate the patch detection problem as a semantic segmentation task such that our model can generalize to patches of any size and shape. We further design a two-stage adversarial training scheme to defend against the stronger adaptive attacks. We thoroughly evaluate PatchZero on the image classification (ImageNet, RESISC45), object detection (PASCAL VOC), and video classification (UCF101) datasets. Our method achieves SOTA robust accuracy without any degradation in the benign performance.
https://arxiv.org/abs/2207.01795
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source Vision-Language pre-trained models in large scales of the model architecture and amount of data. In this study, we focus on transferring knowledge for vision classification tasks. Conventional methods randomly initialize the linear classifier head for vision classification, but they leave the usage of the text encoder for downstream visual recognition tasks undiscovered. In this paper, we revise the role of the linear classifier and replace the classifier with the embedded language representations of the object categories. These language representations are initialized from the text encoder of the vision-language pre-trained model to further utilize its well-pretrained language model parameters. The empirical study shows that our method improves both the performance and the training speed of video classification, with a negligible change in the model. In particular, our paradigm achieves the state-of-the-art accuracy of 87.3% on Kinetics-400.
https://arxiv.org/abs/2207.01297