Abstract

Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at layer-level granularity and show that selectively binarizing the inputs to specific layers in the network could lead to significant improvements in accuracy while preserving most of the advantages of binarization. We analyze the binarization tradeoff using a metric that jointly models the input binarization-error and computational cost and introduce an efficient algorithm to select layers whose inputs are to be binarized. Practical guidelines based on insights obtained from applying the algorithm to a variety of models are discussed. Experiments on Imagenet dataset using AlexNet and ResNet-18 models show 3-4% improvements in accuracy over fully binarized networks with minimal

Abstract

We, humans, have the ability to easily imagine scenes that depict sentences such as “Today is a beautiful sunny day” or “There is a Christmas feel, in the air”. While it is hard to precisely describe what one person may imagine, the essential high-level themes associated with such sentences largely remains the same. The ability to synthesize novel images that depict the feel of a sentence is very useful in a variety of applications such as education, advertisement, and entertainment. While existing papers tackle this problem given a style image, we aim to provide a far more intuitive and easy to use solution that synthesizes novel renditions of an existing image, conditioned on a given sentence. We present a method for cross-modal style transfer between an English sentence and an image, to produce a new image that imbibes the essential theme of the sentence. We do this by modifying the style transfer mechanism

Abstract

A system for capturing horizontal disparity stereo panorama is disclosed . The system includes a multi surface selective light reflector unit , a secondary reflector and a computing unit . The multi surface selective light reflector unit ( a ) obtains light rays from a 3D scene of outside world that are relevant to create ( i ) a left eye panorama and ( ii ) a right eye panorama and ( b ) reflects the light rays without internal reflections between the light rays . The secondary reflector ( a ) obtains the reflected light rays from the multi surface selective light reflector unit and ( b ) reflects the light rays through the viewing aperture . The computing unit captures ( i ) the reflected light rays from the secondary reflector and ( ii ) the upper part of the 3D scene from a concave lens as a warped image and processes the warped image to ( a ) the left eye panorama and ( b ) the right eye panorama .

Abstract

We look at the problem of developing a compact and accurate model for gesture recognition from videos in a deep-learning framework. Towards this we propose a joint 3DCNN-LSTM model that is end-to-end trainable and is shown to be better suited to capture the dynamic information in actions. The solution achieves close to state-of-the-art accuracy on the ChaLearn dataset, with only half the model size. We also explore ways to derive a much more compact representation in a knowledge distillation framework followed by model compression. The final model is less than 1 MB in size, which is less than one hundredth of our initial model, with a drop of 7% in accuracy, and is suitable for real-time gesture recognition on mobile devices.

Abstract

wo-view stereo problem is a well researchedproblem in 3D computer vision. Algorithms proposedin the past have focussed on rectified stereo imageswhere the epipolar lines are parallel to the horizon-tal axis.The general problem of computing stereocorrespondences for unrectified images without anyknowledge of calibration parameters is an importantproblem but unexplored as yet. Our idea in this paperis to predict depth maps from two unrectified stereoimages using a modified Flownet architecture. Since,datasets for depth map reconstruction for unrectifiedstereo images for deep learning do not exist, we havecreated a dataset of turn table sequences of 3D modelsfrom Google 3D warehouse. Following the conceptsof Attention modelling, we implement an architecturefor combining correlations computed at multipleresolutions using a simple element-wise multiplicationof the correlations to aid the architecture to resolvecorrespondences for textureless and repeated texturedsurfaces. Our experiments show both qualitaitve andquantitative improvements of depth maps over theoriginal Flownet architecture.

Abstract

Video highlights are a selection of the most interesting parts of a video. The problem of highlight de-tection has been explored for video domains like egocentric,sports, movies, and surveillance videos. Existing methods are limited to finding visually important parts of the video but does not necessarily learn semantics. Moreover, the available benchmark datasets contain audio muted, single activity,short videos, which lack any context apart from a few keyframes that can be used to understand them. In this work,we explore highlight detection in the TV series domain, which features complex interactions with the surroundings. The existing methods would fare poorly in capturing the video semantics in such videos. To incorporate the importance of dialogues/audio, we propose using the descriptions of shots of the video as cues to learning visual importance.Note that while the audio information is used to determine visual importance during training, the highlight detection still works using only the visual information from videos.We use publicly available text ranking algorithms to rank the descriptions. The ranking scores are used to train a visual pair wise shot ranking model (VPSR) to find the highlights of the video. The results are reported on TV series videos of the Video Set dataset and a season of Buffy the Vampire SlayerTV series.

Abstract

Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work,(i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing.(ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions.(iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.

Abstract

Transgender face recognition is gaining increasing attention in the face recognition community because ofits potential in real life applications. Despite extensive progress in traditional face recognition domain, it is very challenging to recognize faces under transgender setting.The gender transformation results in significant face variations, both in shape and texture gradually over time. This introduces additional complexities to existing face recognition algorithms to achieve a reliable performance. In this paper, we present a novel framework that incorporates appearance factor and a transformation factor caused due to Hormone Replacement Therapy (HRT) for recognition.To this extent, we employ the Hidden Factor Analysis(HFA) to jointly model a face under therapy as a linear combination of appearance and transformation factors.This is based on the intuition that the appearance factor captures the features that are unaffected by the therapy and transformation factor captures the feature changes due to therapy. Extensive experiments carried out on publicly available HRT transgender face database shows the efficacy of the proposed scheme with a recognition accuracy of82.36%

Abstract

We present a practical solution for generating 360◦stereo panoramic videos using a single camera. Current approaches either use a moving camera that captures multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. Our approach improves upon the existing solutions in two significant ways: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a panoramic stereo capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use. We analyze several properties of the design as well as present panoramic stereo and depth estimation results.

Abstract

Fine-grained classification is an extremely challenging problem in computer vision, compounded by subtle differences in shape, pose, illumination and appearance. While convolutional neural networks have become the versatile jack-of-all-trades tool in modern computer vision, approaches for fine-grained recognition still rely on localization of keypoints and parts to learn discriminative features for recognition. In order to achieve this, most approaches use a localization module and subsequently learn classifiers for the inferred locations,thus necessitating large amounts of manual annotations for bounding boxes and key points. In order to tackle this problem,we aim to leverage the (taxonomic and/or semantic) relationships present among fine-grained classes. The ontology tree is a free source of labels that can be used as auxiliary tasks to train a multi-task loss. Additional tasks can act as regularizers, and increase the generalization capabilities of the network. Multiple tasks try to take the network in diverging directions, and the network has to reach a common minimum by adapting and learning features common to all tasks in its shared layers.We train a multi-task network using auxiliary tasks extracted from taxonomical or semantic hierarchies, using a novel method to update task-wise learning rates to ensure that the related tasks aid and unrelated tasks does not hamper performance on the primary task. Experiments on the popular CUB-200-2011 dataset show that employing super-classes in an end-to-end model improves performance, compared to methods employing additional expensive annotations such as key points and bounding boxes and/or using multi-stage pipelines.