Many attempts have been made towards combining RGB and 3D poses for the recognition of Activities of Daily Living (ADL). ADL may look very similar and often necessitate to model fine-grained details to distinguish them. Because the recent 3D ConvNets are too rigid to capture the subtle visual patterns across an action, this research direction is dominated by methods combining RGB and 3D Poses. But the cost of computing 3D poses from RGB stream is high in the absence of appropriate sensors. This limits the usage of aforementioned approaches in real-world applications requiring low latency. Then, how to best take advantage of 3D Poses for recognizing ADL? To this end, we propose an extension of a pose driven attention mechanism: Video-Pose Network (VPN), exploring two distinct directions. One is to transfer the Pose knowledge into RGB through a feature-level distillation and the other towards mimicking pose driven attention through an attention-level distillation. Finally, these two approaches are integrated into a single model, we call VPN++. We show that VPN++ is not only effective but also provides a high speed up and high resilience to noisy Poses. VPN++, with or without 3D Poses, outperforms the representative baselines on 4 public datasets. Code is available at https://github.com/srijandas07/vpnplusplus.
We introduce a weakly supervised method for representation learning based on aligning temporal sequences (e.g., videos) of the same process (e.g., human action). The main idea is to use the global temporal ordering of latent correspondences across sequence pairs as a supervisory signal. In particular, we propose a loss based on scoring the optimal sequence alignment to train an embedding network. Our loss is based on a novel probabilistic path finding view of dynamic time warping (DTW) that contains the following three key features: (i) the local path routing decisions are contrastive and differentiable, (ii) pairwise distances are cast as probabilities that are contrastive as well, and (iii) our formulation naturally admits a global cycle consistency loss that verifies correspondences. For evaluation, we consider the tasks of fine-grained action classification, few shot learning, and video synchronization. We report significant performance increases over previous methods. In addition, we report two applications of our temporal alignment framework, namely 3D pose reconstruction and fine-grained audio/visual retrieval.
Inspired by the fact that human eyes continue to develop tracking ability in early and middle childhood, we propose to use tracking as a proxy task for a computer vision system to learn the visual representations. Modelled on the Catch game played by the children, we design a Catch-the-Patch (CtP) game for a 3D-CNN model to learn visual representations that would help with video-related tasks. In the proposed pretraining framework, we cut an image patch from a given video and let it scale and move according to a pre-set trajectory. The proxy task is to estimate the position and size of the image patch in a sequence of video frames, given only the target bounding box in the first frame. We discover that using multiple image patches simultaneously brings clear benefits. We further increase the difficulty of the game by randomly making patches invisible. Extensive experiments on mainstream benchmarks demonstrate the superior performance of CtP against other video pretraining methods. In addition, CtP-pretrained features are less sensitive to domain gaps than those trained by a supervised action recognition task. When both trained on Kinetics-400, we are pleasantly surprised to find that CtP-pretrained representation achieves much higher action classification accuracy than its fully supervised counterpart on Something-Something dataset. Code is available online: github.com/microsoft/CtP.
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3$\times$ while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention ($pool_{topK\_std}$), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast
We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, single-backbone Transformer by sharing weights among the three modalities. We show that the convolution-free VATT outperforms state-of-the-art ConvNet-based architectures in the downstream tasks. Especially, VATT's vision Transformer achieves the top-1 accuracy of 82.1% on Kinetics-400, 83.6% on Kinetics-600, 72.7% on Kinetics-700, and 41.1% on Moments in Time, new records while avoiding supervised pre-training. Transferring to image classification leads to 78.7% top-1 accuracy on ImageNet compared to 64.7% by training the same Transformer from scratch, showing the generalizability of our model despite the domain gap between videos and images. VATT's audio Transformer also sets a new record on waveform-based audio event recognition by achieving the mAP of 39.4% on AudioSet without any supervised pre-training. VATT's source code is publicly available.
Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each query addresses a particular question, and has its own response label set. We make the following four contributions: (I) We propose a new model - a Temporal Query Network - which enables the query-response functionality, and a structural understanding of fine-grained actions. It attends to relevant segments for each query with a temporal attention mechanism, and can be trained using only the labels for each query. (ii) We propose a new way - stochastic feature bank update - to train a network on videos of various lengths with the dense sampling required to respond to fine-grained queries. (iii) We compare the TQN to other architectures and text supervision methods, and analyze their pros and cons. Finally, (iv) we evaluate the method extensively on the FineGym and Diving48 benchmarks for fine-grained action classification and surpass the state-of-the-art using only RGB features.
A common strategy to video understanding is to incorporate spatial and motion information by fusing features derived from RGB frames and optical flow. In this work, we introduce a new way to leverage semantic segmentation as an intermediate representation for video understanding and use it in a way that requires no additional labeling. Second, we propose a general framework which learns the intermediate representations (optical flow and semantic segmentation) jointly with the final video understanding task and allows the adaptation of the representations to the end goal. Despite the use of intermediate representations within the network, during inference, no additional data beyond RGB sequences is needed, enabling efficient recognition with a single network. Finally, we present a way to find the optimal learning configuration by searching the best loss weighting via evolution. We obtain more powerful visual representations for videos which lead to performance gains over the state-of-the-art.
Detection and localization of actions in videos is an important problem in practice. State-of-the-art video analytics systems are unable to efficiently and effectively answer such action queries because actions often involve a complex interaction between objects and are spread across a sequence of frames; detecting and localizing them requires computationally expensive deep neural networks. It is also important to consider the entire sequence of frames to answer the query effectively. In this paper, we present ZEUS, a video analytics system tailored for answering action queries. We present a novel technique for efficiently answering these queries using deep reinforcement learning. ZEUS trains a reinforcement learning agent that learns to adaptively modify the input video segments that are subsequently sent to an action classification network. The agent alters the input segments along three dimensions - sampling rate, segment length, and resolution. To meet the user-specified accuracy target, ZEUS's query optimizer trains the agent based on an accuracy-aware, aggregate reward function. Evaluation on three diverse video datasets shows that ZEUS outperforms state-of-the-art frame- and window-based filtering techniques by up to 22.1x and 4.7x, respectively. It also consistently meets the user-specified accuracy target across all queries.
This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transferring global attribute or object information from seen to unseen action videos, we seek to classify and spatio-temporally localize unseen actions in videos from image-based object information only. We propose three spatial object priors, which encode local person and object detectors along with their spatial relations. On top we introduce three semantic object priors, which extend semantic matching through word embeddings with three simple functions that tackle semantic ambiguity, object discrimination, and object naming. A video embedding combines the spatial and semantic object priors. It enables us to introduce a new video retrieval task that retrieves action tubes in video collections based on user-specified objects, spatial relations, and object size. Experimental evaluation on five action datasets shows the importance of spatial and semantic object priors for unseen actions. We find that persons and objects have preferred spatial relations that benefit unseen action localization, while using multiple languages and simple object filtering directly improves semantic matching, leading to state-of-the-art results for both unseen action classification and localization.
We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.
Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works focus on creating hand-engineered features from these images or learn such features with deep neural networks in a fully or weakly-supervised framework. Both require prior knowledge or labelled datasets. Therefore, subsequent works propose unsupervised approaches based on generative models to learn these representations. Recently, representations learned with self-supervised contrastive loss-based methods have yielded state-of-the-art results on various imaging tasks compared to earlier unsupervised approaches. In this work, we leverage a contrastive learning framework to learn appropriate representations from single-cell fluorescent microscopy images for the task of Mechanism-of-Action classification. The proposed work is evaluated on the annotated BBBC021 dataset, and we obtain state-of-the-art results in NSC, NCSB and drop metrics for an unsupervised approach. We observe an improvement of 10% in NCSB accuracy and 11% in NSC-NSCB drop over the previously best unsupervised method. Moreover, the performance of our unsupervised approach ties with the best supervised approach. Additionally, we observe that our framework performs well even without post-processing, unlike earlier methods. With this, we conclude that one can learn robust cell representations with contrastive learning.
Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and camera viewpoints. In this paper, we show that current convolutional neural network models are unable to recognize actions from camera viewpoints not present in their training data (i.e., unseen view action recognition). To address this, we develop approaches based on 3D representations and introduce a new geometric convolutional layer that can learn viewpoint invariant representations. Further, we introduce a new, challenging dataset for unseen view recognition and show the approaches ability to learn viewpoint invariant representations.
Temporal action localization (TAL) is a fundamental yet challenging task in video understanding. Existing TAL methods rely on pre-training a video encoder through action classification supervision. This results in a task discrepancy problem for the video encoder -- trained for action classification, but used for TAL. Intuitively, end-to-end model optimization is a good solution. However, this is not operable for TAL subject to the GPU memory constraints, due to the prohibitive computational cost in processing long untrimmed videos. In this paper, we resolve this challenge by introducing a novel low-fidelity end-to-end (LoFi) video encoder pre-training method. Instead of always using the full training configurations for TAL learning, we propose to reduce the mini-batch composition in terms of temporal, spatial or spatio-temporal resolution so that end-to-end optimization for the video encoder becomes operable under the memory conditions of a mid-range hardware budget. Crucially, this enables the gradient to flow backward through the video encoder from a TAL loss supervision, favourably solving the task discrepancy problem and providing more effective feature representations. Extensive experiments show that the proposed LoFi pre-training approach can significantly enhance the performance of existing TAL methods. Encouragingly, even with a lightweight ResNet18 based video encoder in a single RGB stream, our method surpasses two-stream ResNet50 based alternatives with expensive optical flow, often by a good margin.
In video data, busy motion details from moving regions are conveyed within a specific frequency bandwidth in the frequency domain. Meanwhile, the rest of the frequencies of video data are encoded with quiet information with substantial redundancy, which causes low processing efficiency in existing video models that take as input raw RGB frames. In this paper, we consider allocating intenser computation for the processing of the important busy information and less computation for that of the quiet information. We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data. By embedding the MBPM into a two-pathway CNN architecture, we define a Busy-Quiet Net (BQN). The efficiency of BQN is determined by avoiding redundancy in the feature space processed by the two pathways: one operating on Quiet features of low-resolution, while the other processes Busy features. The proposed BQN outperforms many recent video processing models on Something-Something V1, Kinetics400, UCF101 and HMDB51 datasets.
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we release code at https://github.com/google-research/scenic/tree/main/scenic/projects/vivit
Leading methods in the domain of action recognition try to distill information from both the spatial and temporal dimensions of an input video. Methods that reach State of the Art (SotA) accuracy, usually make use of 3D convolution layers as a way to abstract the temporal information from video frames. The use of such convolutions requires sampling short clips from the input video, where each clip is a collection of closely sampled frames. Since each short clip covers a small fraction of an input video, multiple clips are sampled at inference in order to cover the whole temporal length of the video. This leads to increased computational load and is impractical for real-world applications. We address the computational bottleneck by significantly reducing the number of frames required for inference. Our approach relies on a temporal transformer that applies global attention over video frames, and thus better exploits the salient information in each frame. Therefore our approach is very input efficient, and can achieve SotA results (on Kinetics dataset) with a fraction of the data (frames per video), computation and latency. Specifically on Kinetics-400, we reach $80.5$ top-1 accuracy with $\times 30$ less frames per video, and $\times 40$ faster inference than the current leading method. Code is available at: https://github.com/Alibaba-MIIL/STAM
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets and do not support online inference, making them difficult to work on mobile devices. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs. First, we design a video network search space and employ neural architecture search to generate efficient and diverse 3D CNN architectures. Second, we introduce the Stream Buffer technique that decouples memory from video clip duration, allowing 3D CNNs to embed arbitrary-length streaming video sequences for both training and inference with a small constant memory footprint. Third, we propose a simple ensembling technique to improve accuracy further without sacrificing efficiency. These three progressive techniques allow MoViNets to achieve state-of-the-art accuracy and efficiency on the Kinetics, Moments in Time, and Charades video action recognition datasets. For instance, MoViNet-A5-Stream achieves the same accuracy as X3D-XL on Kinetics 600 while requiring 80% fewer FLOPs and 65% less memory. Code will be made available at https://github.com/tensorflow/models/tree/master/official/vision.
Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer two new scaling strategies: (1) scale model depth in regimes where overfitting can occur (width scaling is preferable otherwise); (2) increase image resolution more slowly than previously recommended (Tan & Le, 2019). Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1.7x - 2.7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet. In a large-scale semi-supervised learning setup, ResNet-RS achieves 86.2% top-1 ImageNet accuracy, while being 4.7x faster than EfficientNet NoisyStudent. The training techniques improve transfer performance on a suite of downstream tasks (rivaling state-of-the-art self-supervised algorithms) and extend to video classification on Kinetics-400. We recommend practitioners use these simple revised ResNets as baselines for future research.
Hand action recognition is a special case of action recognition with applications in human-robot interaction, virtual reality or life-logging systems. Building action classifiers able to work for such heterogeneous action domains is very challenging. There are very subtle changes across different actions from a given application but also large variations across domains (e.g. virtual reality vs life-logging). This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. When working on a single domain (intra-domain action classification) our approach performs better or similar to current state-of-the-art methods on well-known hand action recognition benchmarks. And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods. These experiments show the robustness and generalization capabilities of our framework.