Abstract

In this paper, we propose online algorithms for multiclass classification using partial labels. We propose two variants of Perceptron called Avg Perceptron and Max Perceptron to deal with the partially labeled data. We also propose Avg Pegasos and Max Pegasos, which are extensions of the Pegasos algorithm. We also provide mistake bounds for Avg Perceptron and regret bound for Avg Pegasos. We show the effectiveness of the proposed approaches by experimenting on various datasets and comparing them with the standard Perceptron and Pegasos.

Abstract

Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity. In this paper, we propose a pipeline for understanding vehicle behaviour from a monocular image sequence or video. A monocular sequence along with scene semantics, optical flow and object labels are used to get spatial information about the object (vehicle) of interest and other objects (semantically contiguous set of locations) in the scene. This spatial information is encoded by a Multi-Relational Graph Convolutional Network (MR-GCN), and a temporal sequence of such encodings is fed to a recurrent network to label vehicle behaviours. The proposed framework can classify a variety of vehicle behaviours to high fidelity on datasets that are diverse and include European, Chinese and Indian on-road scenes. The framework also provides for seamless transfer of models across datasets without entailing re-annotation, retraining and even fine-tuning. We show comparative performance gain over baseline Spatio-temporal classifiers and detail a variety of ablations to showcase the efficacy of the framework.

Abstract

We present a novel Multi Relational Graph Convolutional Network (MRGCN) to model on-road vehicle behaviours from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a Multi Relational Graph (MRG) where the nodes of the graph represent the active and passive participants/agents in the scene while the bidrectional edges that connect every pair of nodes are encodings of the spatio-temporal relations. The bidirectional edges of the graph encode the temporal interactions between the agents that constitute the two nodes of the edge. The proposed method of obtaining his encoding is shown to be specifically suited for the problem at hand as it outperforms more complex end to end learning methods that do not use such intermediate representations of evolved spatio-temporal relations between agent pairs. We show significant performance gain in the form of behaviour classification accuracy on a variety of datasets from different parts of the globe over prior methods as well as show seamless transfer without any resort to fine-tuning across multiple datasets. Such behaviour prediction methods find immediate relevance in a variety of navigation tasks such as behaviour planning, state estimation as well as in applications relating to detection of traffic violations over videos.

Abstract

Object detection has been at the forefront for higher level vision tasks such as scene understanding and contextual reasoning. Therefore, solving object detection for a large number of visual categories is paramount. Zero-Shot Object Detection (ZSD) – where training data is not available for some of the target classes – provides semantic scalability to object detection and reduces dependence on large amount of annotations, thus enabling a large number of applications in real-life scenarios. In this paper, we propose a novel multi-space approach to solve ZSD where we combine predictions obtained in two different search spaces. We learn the projection of visual features of proposals to the semantic embedding space and class labels in the semantic embedding space to visual space. We predict similarity scores in the individual spaces and combine them. We present promising results on two datasets, PASCAL VOC and MS COCO. We further discuss the problem of hubness and show that our approach alleviates hubness with a performance superior to previously proposed methods

Abstract

Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural speech given only the lip movements of a speaker. Acknowledging the importance of contextual and speakerspecific cues for accurate lip-reading, we take a different path from existing works. We focus on learning accurate lip sequences to speech mappings for individual speakers in unconstrained, large vocabulary settings. To this end, we collect and release a large-scale benchmark dataset, the first of its kind, specifically to train and evaluate the singlespeaker lip to speech task in natural settings. We propose a novel approach with key design choices to achieve accurate, natural lip to speech synthesis in such unconstrained scenarios for the first time. Extensive evaluation using quantitative, qualitative metrics and human evaluation shows that our method is four times more intelligible than previous works in this space.

Abstract

No Results Found

Abstract

We present sentence aligned parallel corpora across 10 Indian Languages - Hindi, Telugu, Tamil, Malayalam, Gujarati, Urdu, Bengali, Oriya, Marathi, Punjabi, and English - many of which are categorized as low resource. The corpora are compiled from online sources which have content shared across languages. The corpora presented significantly extends present resources that are either not large enough or are restricted to a specific domain (such as health). We also provide a separate test corpus compiled from an independent online source that can be independently used for validating the performance in 10 Indian languages. Alongside, we report on the methods of constructing such corpora using tools enabled by recent advances in machine translation and cross-lingual retrieval using deep neural network based methods.

Abstract

Abstract— Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new ”RoadText-1K” dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection, recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/ projects/cvit-projects/roadtext-1k

Abstract

We present a new dataset for Visual Question Answering on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. We provide detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document in crucial.

Abstract

Autonomous camera systems are often subjected to an optimization/filtering operation to smoothen and stabilize the rough trajectory estimates. Most common filtering techniques do reduce the irregularities in data; however, they fail to mimic the behavior of a human cameraman. Global filtering methods modeling human camera operators have been successful; however, they are limited to offline settings. In this paper, we propose two online filtering methods called Cinefilters, which produce smooth camera trajectories that are motivated by cinematographic principles. The first filter (CineConvex) uses a sliding window-based convex optimization formulation, and the second (CineCNN) is a CNN based encoder-decoder model. We evaluate the proposed filters in two different settings, namely a basketball dataset and a stage performance dataset. Our models outperform previous methods and baselines on both quantitative and qualitative metrics. The CineConvex and CineCNN filters operate at about 250fps and 1000fps, respectively, with a minor latency (half a second), making them apt for a variety of real-time applications.