Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap hardware and a focus on the visual modality, and may have been post-processed or edited. In this paper, we extend our earlier work on adapting the acoustic model of a DNN-based speech recognition system to an RNN language model and show how both can be adapted to the objects and scenes that can be automatically detected in the video. We are working on a corpus of "how-to" videos from the web, and the idea is that an object that can be seen ("car"), or a scene that is being detected ("kitchen") can be used to condition both models on the "context" of the recording, thereby reducing perplexity and improving transcription. We achieve good improvements in both cases and compare and analyze the respective reductions in word error rate. We expect that our results can be used for any type of speech processing in which "context" information is available, for example in robotics, man-machine interaction, or when indexing large audio-visual archives, and should ultimately help to bring together the "video-to-text" and "speech-to-text" communities.
In recent years, we have seen tremendous progress in the field of object detection. Most of the recent improvements have been achieved by targeting deeper feedforward networks. However, many hard object categories such as bottle, remote, etc. require representation of fine details and not just coarse, semantic representations. But most of these fine details are lost in the early convolutional layers. What we need is a way to incorporate finer details from lower layers into the detection architecture. Skip connections have been proposed to combine high-level and low-level features, but we argue that selecting the right features from low-level requires top-down contextual information. Inspired by the human visual pathway, in this paper we propose top-down modulations as a way to incorporate fine details into the detection framework. Our approach supplements the standard bottom-up, feedforward ConvNet with a top-down modulation (TDM) network, connected using lateral connections. These connections are responsible for the modulation of lower layer filters, and the top-down network handles the selection and integration of contextual information and low-level features. The proposed TDM architecture provides a significant boost on the COCO testdev benchmark, achieving 28.6 AP for VGG16, 35.2 AP for ResNet101, and 37.3 for InceptionResNetv2 network, without any bells and whistles (e.g., multi-scale, iterative box refinement, etc.).
A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. We propose learning these through interacting with a visual and dynamic environment. Our proposed solution involves bootstrapping reinforcement learning with imitation learning. To ensure cross task generalization, we develop a deep predictive model based on successor representations. Our experimental results show near optimal results across a wide range of tasks in the challenging THOR environment.
Learning visual representations with self-supervised learning has become popular in computer vision. The idea is to design auxiliary tasks where labels are free to obtain. Most of these tasks end up providing data to learn specific kinds of invariance useful for recognition. In this paper, we propose to exploit different self-supervised approaches to learn representations invariant to (i) inter-instance variations (two objects in the same class should have similar features) and (ii) intra-instance variations (viewpoint, pose, deformations, illumination, etc). Instead of combining two approaches with multi-task learning, we argue to organize and reason the data with multiple variations. Specifically, we propose to generate a graph with millions of objects mined from hundreds of thousands of videos. The objects are connected by two types of edges which correspond to two types of invariance: "different instances but a similar viewpoint and category" and "different viewpoints of the same instance". By applying simple transitivity on the graph with these edges, we can obtain pairs of images exhibiting richer visual invariance. We use this data to train a Triplet-Siamese network with VGG16 as the base architecture and apply the learned representations to different recognition tasks. For object detection, we achieve 63.2% mAP on PASCAL VOC 2007 using Fast R-CNN (compare to 67.3% with ImageNet pre-training). For the challenging COCO dataset, our method is surprisingly close (23.5%) to the ImageNet-supervised counterpart (24.4%) using the Faster R-CNN framework. We also show that our network can perform significantly better than the ImageNet network in the surface normal estimation task.
What is the right way to reason about human activities? What directions forward are most promising? In this work, we analyze the current state of human activity understanding in videos. The goal of this paper is to examine datasets, evaluation metrics, algorithms, and potential future directions. We look at the qualitative attributes that define activities such as pose variability, brevity, and density. The experiments consider multiple state-of-the-art algorithms and multiple datasets. The results demonstrate that while there is inherent ambiguity in the temporal extent of activities, current datasets still permit effective benchmarking. We discover that fine-grained understanding of objects and pose when combined with temporal reasoning is likely to yield substantial improvements in algorithmic accuracy. We present the many kinds of information that will be needed to achieve substantial gains in activity understanding: objects, verbs, intent, and sequential reasoning. The software and additional information will be made available to provide other researchers detailed diagnostics to understand their own algorithms.
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10x or 100x? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between `enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.
The massive explosion and ubiquity of computing devices and the outreach of the web have been the most defining events of the century so far. As more and more people gain access to the internet, traditional know-something and have-something authentication methods such as PINs and passwords are proving to be insufficient for prohibiting unauthorized access to increasingly personal data on the web. Therefore, the need of the hour is a user-verification system that is not only more reliable and secure, but also unobtrusive and minimalistic. Keystroke Dynamics is a novel Biometric Technique; it is not only unobtrusive, but also transparent and inexpensive. The fusion of keystroke dynamics and Face Recognition engenders the most desirable characteristics of a verification system. Our implementation uses Hidden Markov Models (HMM) for modelling the Keystroke Dynamics, with the help of two widely used Feature Vectors: Keypress Latency and Keypress Duration. On the other hand, Face Recognition makes use of the traditional Eigenfaces approach.The results show that the system has a high precision, with a False Acceptance Rate of 5.4% and a False Rejection Rate of 9.2%. Moreover, it is also future-proof, as the hardware requirements, i.e. camera and keyboard (physical or on-screen), have become an indispensable part of modern computing.
In this paper, we investigate a weakly-supervised object detection framework. Most existing frameworks focus on using static images to learn object detectors. However, these detectors often fail to generalize to videos because of the existing domain shift. Therefore, we investigate learning these detectors directly from boring videos of daily activities. Instead of using bounding boxes, we explore the use of action descriptions as supervision since they are relatively easy to gather. A common issue, however, is that objects of interest that are not involved in human actions are often absent in global action descriptions known as "missing label". To tackle this problem, we propose a novel temporal dynamic graph Long Short-Term Memory network (TD-Graph LSTM). TD-Graph LSTM enables global temporal reasoning by constructing a dynamic graph that is based on temporal correlations of object proposals and spans the entire video. The missing label issue for each individual frame can thus be significantly alleviated by transferring knowledge across correlated objects proposals in the whole video. Extensive evaluations on a large-scale daily-life action dataset (i.e., Charades) demonstrates the superiority of our proposed method. We also release object bounding-box annotations for more than 5,000 frames in Charades. We believe this annotated data can also benefit other research on video-based object recognition in the future.
Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of activities, as well as the higher-level constructs such as intentions. But how do we model and reason about these? We propose a fully-connected temporal CRF model for reasoning over various aspects of activities that includes objects, actions, and intentions, where the potentials are predicted by a deep network. End-to-end training of such structured models is a challenging endeavor: For inference and learning we need to construct mini-batches consisting of whole videos, leading to mini-batches with only a few videos. This causes high-correlation between data points leading to breakdown of the backprop algorithm. To address this challenge, we present an asynchronous variational inference method that allows efficient end-to-end training. Our method achieves a classification mAP of 22.4% on the Charades benchmark, outperforming the state-of-the-art (17.2% mAP), and offers equal gains on the task of temporal localization.
We present the 2017 WebVision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the spirit of previous vision challenges, such as ILSVRC, Places2 and PASCAL VOC, which have played critical roles in the development of computer vision by contributing to the community with large scale annotated data for model designing and standardized benchmarking, we contribute with this challenge a large scale web images dataset, and a public competition with a workshop co-located with CVPR 2017. The WebVision dataset contains more than $2.4$ million web images crawled from the Internet by using queries generated from the $1,000$ semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information is also included. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset. In this paper, we describe the details of data collection and annotation, highlight the characteristics of the dataset, and introduce the evaluation metrics.