Sudheendra Vijayanarasimhan

Sudheendra Vijayanarasimhan

Sudheendra received his Ph.D. in Computer Science from the University of Texas at Austin in 2011 where his research focused on Active learning in Computer Vision and joined Google in 2011. His current work at Google Research is focused on Video Classification and Action Recognition. His past projects include scaling up object detection and neural networks classification and the design of neural-network architectures for video classification.

Research Areas

Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Preview abstract This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly. AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding. View details
    Preview abstract We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late is important. We achieve state-of-the-art performance for both action proposal and localiza- tion on THUMOS’14 detection benchmark and competitive performance on ActivityNet challenge. View details
    End-to-End Learning of Semantic Grasping
    Eric Jang
    Julian Ibarz
    Peter Pastor Sampedro
    Sergey Levine
    CoRL 2017(2017) (to appear)
    Preview abstract We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis of visual reasoning, we present a semantic grasping framework that learns object detection, classification, and grasp planning in an end-to-end fashion. A ``ventral stream'' recognizes object class while a ``dorsal stream'' simultaneously interprets the geometric relationships necessary to execute successful grasps. We leverage the autonomous data collection capabilities of robots to obtain a large self-supervised dataset for training the dorsal stream, and use semi-supervised label propagation to train the ventral stream with only a modest amount of human supervision. We experimentally show that our approach exhibits an improvement in accuracy over grasping systems whose components are not learned end-to-end, including a baseline method that uses bounding box detection. Furthermore, we show that jointly training our model with auxiliary data consisting of non-semantic grasping data, as well as semantically labeled images without grasp actions, has the potential to substantially improve semantic grasping performance. View details
    Preview abstract We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-toframe pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of frames, SfM-Net predicts depth, segmentation, camera and rigid object motions, converts those into a dense frame-to-frame motion field (optical flow), differentiably warps frames in time to match pixels and backpropagates. The model can be trained with various degrees of supervision: 1) completely unsupervised, 2) supervised by ego-motion (camera motion), 3) supervised by depth (e.g., as provided by RGBD sensors), 4) supervised by ground-truth optical flow. We show that SfM-Net successfully estimates segmentation of the objects in the scene, even though such supervision is never provided. It extracts meaningful depth estimates or infills depth of RGBD sensors and successfully estimates frame-to-frame camera displacements. SfM-Net achieves state-of-the-art optical flow performance. Our work is inspired by the long history of research in geometry-aware motion estimation, Simultaneous Localization and Mapping (SLAM) and Structure from Motion (SfM). SfM-Net is an important first step towards providing a learning-based approach for such tasks. A major benefit over the existing optimization approaches is that our proposed method can improve itself by processing more videos, and by learning to explicitly model moving objects in dynamic scenes. View details
    The Kinetics Human Action Video Dataset
    Andrew Zisserman
    Joao Carreira
    Karen Simonyan
    Will Kay
    Brian Zhang
    Chloe Hillier
    Fabio Viola
    Tim Green
    Trevor Back
    Mustafa Suleyman
    arXiv(2017)
    Preview abstract We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands. We describe the statistics of the dataset, how it was collected, and give some baseline performance figures for neural network architectures trained and tested for human action classification on this dataset. View details
    Preview abstract Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale. It is possible to train models over millions of examples within a few days. Although large-scale datasets exist for image understanding, such as ImageNet, there are no comparable size video classification datasets. In this paper, we introduce YouTube-8M, the largest multi-label video classification dataset, composed of ~8 million videos---500K hours of video---annotated with a vocabulary of 4803 visual entities. To get the videos and their (multiple) labels, we used the YouTube Data APIs. We filtered the video labels (Freebase topics) using both automated and manual curation strategies, including by asking Mechanical Turk workers if the labels are visually recognizable. Then, we decoded each video at one-frame-per-second, and used a Deep CNN pre-trained on ImageNet to extract the hidden representation immediately prior to the classification layer. Finally, we compressed the frame features and make both the features and video-level labels available for download. The dataset contains frame-level features for over 1.9 billion video frames and 8 million videos, making it the largest public multi-label video dataset. We trained various (modest) classification models on the dataset, evaluated them using popular evaluation metrics, and report them as baselines. Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using the publicly-available TensorFlow framework. We plan to release code for training a basic TensorFlow model and for computing metrics. We show that pre-training on large data generalizes to other datasets like Sports-1M and ActivityNet. We achieve state-of-the-art on ActivityNet, improving mAP from 53.8% to 77.8%. We hope that the unprecedented scale and diversity of YouTube-8M will lead to advances in video understanding and representation learning. View details
    Beyond Short Snippets: Deep Networks for Video Classification
    Joe Yue-Hei Ng
    Matthew Hausknecht
    Rajat Monga
    Computer Vision and Pattern Recognition(2015)
    Preview abstract Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 72.8%). View details
    Deep Networks With Large Output Spaces
    Jonathon Shlens
    Rajat Monga
    International Conference on Learning Representations(2015)
    Preview abstract Deep neural networks have been extremely successful at various image, speech, video recognition tasks because of their ability to model deep structures within the data. However, they are still prohibitively expensive to train and apply for problems containing millions of classes in the output layer. Based on the observation that the key computation common to most neural network layers is a vector/matrix product, we propose a fast locality-sensitive hashing technique to approximate the actual dot product enabling us to scale up the training and inference to millions of output classes. We evaluate our technique on three diverse large-scale recognition tasks and show that our approach can train large-scale models at a faster rate (in terms of steps/total time) compared to baseline methods. View details
    Efficient Large Scale Video Classification
    Balakrishnan Varadarajan
    dblp computer science bibliography, http://dblp.org(2015) (to appear)
    Preview abstract Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks (CNNs) which produce competitive results with hand- crafted motion features. These networks were adapted to use video frames in various ways and have yielded state of the art classification results. We present two methods that build on this work, and scale it up to work with millions of videos and hundreds of thousands of classes while maintaining a low computational cost. In the context of large scale video processing, training CNNs on video frames is extremely time consuming, due to the large number of frames involved. We propose to avoid this problem by training CNNs on either YouTube thumbnails or Flickr images, and then using these networks' outputs as features for other higher level classifiers. We discuss the challenges of achieving this and propose two models for frame-level and video-level classification. The first is a highly efficient mixture of experts while the latter is based on long short term memory neural networks. We present results on the Sports-1M video dataset (1 million videos, 487 classes) and on a new dataset which has 12 million videos and 150,000 labels. View details
    Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
    Thomas Dean
    Mark Ruzon
    Mark Segal
    Jonathon Shlens
    Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, USA(2013)
    Preview abstract Many object detection systems are constrained by the time required to convolve a target image with a bank of filters that code for different aspects of an object's appearance, such as the presence of component parts. We exploit locality-sensitive hashing to replace the dot-product kernel operator in the convolution with a fixed number of hash-table probes that effectively sample all of the filter responses in time independent of the size of the filter bank. To show the effectiveness of the technique, we apply it to evaluate 100,000 deformable-part models requiring over a million (part) filters on multiple scales of a target image in less than 20 seconds using a single multi-core processor with 20GB of RAM. This represents a speed-up of approximately 20,000 times - four orders of magnitude - when compared with performing the convolutions explicitly on the same hardware. While mean average precision over the full set of 100,000 object classes is around 0.16 due in large part to the challenges in gathering training data and collecting ground truth for so many classes, we achieve a mAP of at least 0.20 on a third of the classes and 0.30 or better on about 20% of the classes. View details
    Fast, Accurate Detection of 100,000 Object Classes on a Single Machine: Technical Supplement
    Thomas Dean
    Mark Ruzon
    Mark Segal
    Jonathon Shlens
    Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, USA(2013)
    Preview abstract In the companion paper published in CVPR 2013, we presented a method that can directly use deformable part models (DPMs) trained as in [Felzenszwalb et al CVPR 2008]. After training, HOG based part filters are hashed, and, during inference, counts of hashing collisions summed over all hash bands serve as a proxy for part-filter / sliding-window dot products, i.e., filter responses. These counts are an approximation and so we take the original HOG-based filters for the top hash counts and calculate the exact dot products for scoring. It is possible to train DPM models not on HOG data but on a hashed WTA [Yagnik et al ICCV 2011] version of this data. The resulting part filters are sparse, real-valued vectors the size of WTA vectors computed from sliding windows. Given the WTA hash of a window, we exactly recover dot products of the top responses using an extension of locality-sensitive hashing. In this supplement, we sketch a method for training such WTA-based models. View details
    Weakly Supervised Learning of Object Segmentations from Web-Scale Video
    Glenn Hartmann
    Judy Hoffman
    David Tsai
    Omid Madani
    James Rehg
    Rahul Sukthankar
    ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I, Springer-Verlag, Berlin, Heidelberg(2012), pp. 198-208
    Preview abstract We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specifically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as "dog", without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classifiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classifiers are further refined using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we confirm that our proposed methods can learn good object masks just by watching YouTube. View details
    No Results Found