Gaurav Sharma

Jue Lin, Gaurav Sharma, Thrasyvoulos N. Pappas

We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of broader range of textures, from those with regular structures to completely stochastic ones. To train and evaluate the proposed approach, we construct a comprehensive high-resolution dataset that captures the diversity of natural textures as well as stochastic variations within each perceptually uniform texture. Experimental results demonstrate that the proposed approach yields significantly better quality textures than the state of the art. The ultimate goal of this work is a comprehensive understanding of texture space.

Jue Lin, Gaurav Sharma, Thrasyvoulos N. Pappas

We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We adopt StyleGAN3 for synthesis and demonstrate that it produces diverse textures beyond those represented in the training data. For texture analysis, we propose GAN inversion using a novel latent domain reconstruction consistency criterion for synthesized textures, and iterative refinement with Gramian loss for real textures. We propose perceptual procedures for evaluating network capabilities, exploring the global and local behavior of latent space trajectories, and comparing with existing texture analysis-synthesis techniques.

Vasu Goel, Dhruv Sahnan, Venktesh V et al.

Online education platforms are powered by various NLP pipelines, which utilize models like BERT to aid in content curation. Since the inception of the pre-trained language models like BERT, there have also been many efforts toward adapting these pre-trained models to specific domains. However, there has not been a model specifically adapted for the education domain (particularly K-12) across subjects to the best of our knowledge. In this work, we propose to train a language model on a corpus of data curated by us across multiple subjects from various sources for K-12 education. We also evaluate our model, K12-BERT, on downstream tasks like hierarchical taxonomy tagging.

Shirong Liu, Chenjia Bai, Zixian Guo et al.

Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly conservative policies that resemble the behavior policy, thus limiting their performance. We investigate this limitation and attribute it to the static nature of traditional constraints. In this paper, we propose a novel dynamic policy constraint that restricts the learned policy on the samples generated by the exponential moving average of previously learned policies. By integrating this self-constraint mechanism into off-policy methods, our method facilitates the learning of non-conservative policies while avoiding policy collapse in the offline setting. Theoretical results show that our approach results in a nearly monotonically improved reference policy. Extensive experiments on the D4RL MuJoCo domain demonstrate that our proposed method achieves state-of-the-art performance among the policy constraint methods.

Ajinkya Shinde, Gaurav Sharma, Manisha Pattanaik et al.

LiDAR-based sensors employing optical spectrum signals play a vital role in providing significant information about the target objects in autonomous driving vehicle systems. However, the presence of fog in the atmosphere severely degrades the overall system's performance. This manuscript analyzes the role of fog particle size distributions in 3D object detection under adverse weather conditions. We utilise Mie theory and meteorological optical range (MOR) to calculate the attenuation and backscattering coefficient values for point cloud generation and analyze the overall system's accuracy in Car, Cyclist, and Pedestrian case scenarios under easy, medium and hard detection difficulties. Gamma and Junge (Power-Law) distributions are employed to mathematically model the fog particle size distribution under strong and moderate advection fog environments. Subsequently, we modified the KITTI dataset based on the backscattering coefficient values and trained it on the PV-RCNN++ deep neural network model for Car, Cyclist, and Pedestrian cases under different detection difficulties. The result analysis shows a significant variation in the system's accuracy concerning the changes in target object dimensionality, the nature of the fog environment and increasing detection difficulties, with the Car exhibiting the highest accuracy of around 99% and the Pedestrian showing the lowest accuracy of around 73%.

Hao Zhang, Yang Liu, Xiaoyan Liu et al.

We introduce a novel graph-based framework for alleviating key challenges in distantly-supervised relation extraction and demonstrate its effectiveness in the challenging and important domain of biomedical data. Specifically, we propose a graph view of sentence bags referring to an entity pair, which enables message-passing based aggregation of information related to the entity pair over the sentence bag. The proposed framework alleviates the common problem of noisy labeling in distantly supervised relation extraction and also effectively incorporates inter-dependencies between sentences within a bag. Extensive experiments on two large-scale biomedical relation datasets and the widely utilized NYT dataset demonstrate that our proposed framework significantly outperforms the state-of-the-art methods for biomedical distant supervision relation extraction while also providing excellent performance for relation extraction in the general text mining domain.

Siddharth Srivastava, Gaurav Sharma

Majority of research in learning based methods has been towards designing and training networks for specific tasks. However, many of the learning based tasks, across modalities, share commonalities and could be potentially tackled in a joint framework. We present an approach in such direction, to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We first pre-train it by self-supervised masked training, followed by sequential training for the different tasks. We train the network on all major modalities, e.g.\ visual, audio, text and 3D, and report results on $22$ diverse and challenging public benchmarks. We demonstrate empirically that, using a joint network to train across modalities leads to meaningful information sharing and this allows us to achieve state-of-the-art results on most of the benchmarks. We also show generalization of the trained network on cross-modal tasks as well as unseen datasets and tasks.

Zhiqi Pang, Lingling Zhao, Yang Liu et al.

We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) within a single coherent framework. To tackle UMS-ReID, we introduce image-text knowledge modeling (ITKM) -- a three-stage framework that effectively exploits the representational power of vision-language models. We start with a pre-trained CLIP model with an image encoder and a text encoder. In Stage I, we introduce a scenario embedding in the image encoder and fine-tune the encoder to adaptively leverage knowledge from multiple scenarios. In Stage II, we optimize a set of learned text embeddings to associate with pseudo-labels from Stage I and introduce a multi-scenario separation loss to increase the divergence between inter-scenario text representations. In Stage III, we first introduce cluster-level and instance-level heterogeneous matching modules to obtain reliable heterogeneous positive pairs (e.g., a visible image and an infrared image of the same person) within each scenario. Next, we propose a dynamic text representation update strategy to maintain consistency between text and image supervision signals. Experimental results across multiple scenarios demonstrate the superiority and generalizability of ITKM; it not only outperforms existing scenario-specific methods but also enhances overall performance by integrating knowledge from multiple scenarios.

Yuhao Zhu, Ethan Chen, Colin Hascup et al.

We propose an assistive technology that helps individuals with Color Vision Deficiencies (CVD) to recognize/name colors. A dichromat's color perception is a reduced two-dimensional (2D) subset of a normal trichromat's three dimensional color (3D) perception, leading to confusion when visual stimuli that appear identical to the dichromat are referred to by different color names. Using our proposed system, CVD individuals can interactively induce distinct perceptual changes to originally confusing colors via a computational color space transformation. By combining their original 2D precepts for colors with the discriminative changes, a three dimensional color space is reconstructed, where the dichromat can learn to resolve color name confusions and accurately recognize colors. Our system is implemented as an Augmented Reality (AR) interface on smartphones, where users interactively control the rotation through swipe gestures and observe the induced color shifts in the camera view or in a displayed image. Through psychophysical experiments and a longitudinal user study, we demonstrate that such rotational color shifts have discriminative power (initially confusing colors become distinct under rotation) and exhibit structured perceptual shifts dichromats can learn with modest training. The AR App is also evaluated in two real-world scenarios (building with lego blocks and interpreting artistic works); users all report positive experience in using the App to recognize object colors that they otherwise could not.

Gaurav Sharma, Ravi Kothari, Josef Schmid

In this paper, we propose a Neural Radiance Fields (NeRF) based framework, referred to as Novel View Synthesis Framework (NVSF). It jointly learns the implicit neural representation of space and time-varying scene for both LiDAR and Camera. We test this on a real-world autonomous driving scenario containing both static and dynamic scenes. Compared to existing multimodal dynamic NeRFs, our framework is self-supervised, thus eliminating the need for 3D labels. For efficient training and faster convergence, we introduce heuristic-based image pixel sampling to focus on pixels with rich information. To preserve the local features of LiDAR points, a Double Gradient based mask is employed. Extensive experiments on the KITTI-360 dataset show that, compared to the baseline models, our framework has reported best performance on both LiDAR and Camera domain. Code of the model is available at https://github.com/gaurav00700/Selfsupervised-NVSF

Tianming Liang, Yang Liu, Xiaoyan Liu et al.

Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction. The pre-processed datasets and source code are publicly available at https://github.com/tmliang/CGRE.

Siddharth Srivastava, Gaurav Sharma

We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, time series, tabular, graph, X-ray, infrared, IMU, and hyperspectral. The proposed approach utilizes modality specialized tokenizers, a shared transformer architecture, and cross-attention mechanisms to project the data from different modalities into a unified embedding space. It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for different tasks in respective modalities. We propose a novel pretraining strategy with iterative modality switching to initialize the network, and a training algorithm which trades off fully joint training over all modalities, with training on pairs of modalities at a time. We provide comprehensive evaluation across 25 datasets from 12 modalities and show state of the art performances, demonstrating the effectiveness of the proposed architecture, pretraining strategy and adapted multitask training.

Guillaume Letellier, Siddharth Srivastava, Frédéric Jurie et al.

Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become powerful general-purpose feature extractors. However, their immense size and computational cost make them prohibitive for deployment on edge devices such as robots and AR/VR headsets. Existing compression techniques like standard knowledge distillation create efficient 'specialist' models but sacrifice the crucial, downstream-agnostic generality that makes foundation models so valuable. In this paper, we introduce Foundation Model Distillation (FMD), a new paradigm for compressing large SSL models into compact, efficient, and faithful proxies that retain their general-purpose representational power. We present Foundry, the first implementation of FMD for 3D point clouds. Our approach, Foundry, trains a student to learn a compressed set of SuperTokens that reconstruct the teacher's token-level representations, capturing a compact basis of its latent space. A single distilled model maintains strong transferability across diverse downstream tasks-classification, part segmentation, and few-shot scenarios-approaching full foundation-model performance while using significantly fewer tokens and FLOPs, making such models more practical for deployment on resourceconstrained hardware.

Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma

We present StyleClone, a method for training image-to-image translation networks to stylize faces in a specific style, even with limited style images. Our approach leverages textual inversion and diffusion-based guided image generation to augment small style datasets. By systematically generating diverse style samples guided by both the original style images and real face images, we significantly enhance the diversity of the style dataset. Using this augmented dataset, we train fast image-to-image translation networks that outperform diffusion-based methods in speed and quality. Experiments on multiple styles demonstrate that our method improves stylization quality, better preserves source image content, and significantly accelerates inference. Additionally, we provide a systematic evaluation of the augmentation techniques and their impact on stylization performance.

Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma

We propose a method for the task of text-conditioned speech insertion, i.e. inserting a speech sample in an input speech sample, conditioned on the corresponding complete text transcript. An example use case of the task would be to update the speech audio when corrections are done on the corresponding text transcript. The proposed method follows a transformer-based non-autoregressive approach that allows speech insertions of variable lengths, which are dynamically determined during inference, based on the text transcript and tempo of the available partial input. It is capable of maintaining the speaker's voice characteristics, prosody and other spectral properties of the available speech input. Results from our experiments and user study on LibriTTS show that our method outperforms baselines based on an existing adaptive text to speech method. We also provide numerous qualitative results to appreciate the quality of the output from the proposed method.

Shaswata Mahernob Sarkar, Sheikh Iftekhar Ahmed, Jishnu Mahmud et al.

Quantum Machine Learning (QML) has seen significant advancements, driven by recent improvements in Noisy Intermediate-Scale Quantum (NISQ) devices. Leveraging quantum principles such as entanglement and superposition, quantum convolutional neural networks (QCNNs) have demonstrated promising results in classifying both quantum and classical data. This study examines QCNNs in the context of image classification and proposes a novel strategy to enhance feature processing and a QCNN architecture for improved classification accuracy. First, a selective feature re-encoding strategy is proposed, which directs the quantum circuits to prioritize the most informative features, thereby effectively navigating the crucial regions of the Hilbert space to find the optimal solution space. Secondly, a novel parallel-mode QCNN architecture is designed to simultaneously incorporate features extracted by two classical methods, Principal Component Analysis (PCA) and Autoencoders, within a unified training scheme. The joint optimization involved in the training process allows the QCNN to benefit from complementary feature representations, enabling better mutual readjustment of model parameters. To assess these methodologies, comprehensive experiments have been performed using the widely used MNIST and Fashion MNIST datasets for binary classification tasks. Experimental findings reveal that the selective feature re-encoding method significantly improves the quantum circuit's feature processing capability and performance. Furthermore, the jointly optimized parallel QCNN architecture consistently outperforms the individual QCNN models and the traditional ensemble approach involving independent learning followed by decision fusion, confirming its superior accuracy and generalization capabilities.

Prasen Kumar Sharma, Neeraj Matiyali, Siddharth Srivastava et al.

We introduce \textit{Preserve Anything}, a novel method for controlled image synthesis that addresses key limitations in object preservation and semantic consistency in text-to-image (T2I) generation. Existing approaches often fail (i) to preserve multiple objects with fidelity, (ii) maintain semantic alignment with prompts, or (iii) provide explicit control over scene composition. To overcome these challenges, the proposed method employs an N-channel ControlNet that integrates (i) object preservation with size and placement agnosticism, color and detail retention, and artifact elimination, (ii) high-resolution, semantically consistent backgrounds with accurate shadows, lighting, and prompt adherence, and (iii) explicit user control over background layouts and lighting conditions. Key components of our framework include object preservation and background guidance modules, enforcing lighting consistency and a high-frequency overlay module to retain fine details while mitigating unwanted artifacts. We introduce a benchmark dataset consisting of 240K natural images filtered for aesthetic quality and 18K 3D-rendered synthetic images with metadata such as lighting, camera angles, and object relationships. This dataset addresses the deficiencies of existing benchmarks and allows a complete evaluation. Empirical results demonstrate that our method achieves state-of-the-art performance, significantly improving feature-space fidelity (FID 15.26) and semantic alignment (CLIP-S 32.85) while maintaining competitive aesthetic quality. We also conducted a user study to demonstrate the efficacy of the proposed work on unseen benchmark and observed a remarkable improvement of $\sim25\%$, $\sim19\%$, $\sim13\%$, and $\sim14\%$ in terms of prompt alignment, photorealism, the presence of AI artifacts, and natural aesthetics over existing works.

Protyay Dey, Rejoy Chakraborty, Abhilasha S. Jadhav et al.

Source camera model identification (SCMI) plays a pivotal role in image forensics with applications including authenticity verification and copyright protection. For identifying the camera model used to capture a given image, we propose SPAIR-Swin, a novel model combining a modified spatial attention mechanism and inverted residual block (SPAIR) with a Swin Transformer. SPAIR-Swin effectively captures both global and local features, enabling robust identification of artifacts such as noise patterns that are particularly effective for SCMI. Additionally, unlike conventional methods focusing on homogeneous patches, we propose a patch selection strategy for SCMI that emphasizes high-entropy regions rich in patterns and textures. Extensive evaluations on four benchmark SCMI datasets demonstrate that SPAIR-Swin outperforms existing methods, achieving patch-level accuracies of 99.45%, 98.39%, 99.45%, and 97.46% and image-level accuracies of 99.87%, 99.32%, 100%, and 98.61% on the Dresden, Vision, Forchheim, and Socrates datasets, respectively. Our findings highlight that high-entropy patches, which contain high-frequency information such as edge sharpness, noise, and compression artifacts, are more favorable in improving SCMI accuracy. Code will be made available upon request.

Kranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

Binaural audio gives the listener an immersive experience and can enhance augmented and virtual reality. However, recording binaural audio requires specialized setup with a dummy human head having microphones in left and right ears. Such a recording setup is difficult to build and setup, therefore mono audio has become the preferred choice in common devices. To obtain the same impact as binaural audio, recent efforts have been directed towards lifting mono audio to binaural audio conditioned on the visual input from the scene. Such approaches have not used an important cue for the task: the distance of different sound producing objects from the microphones. In this work, we argue that depth map of the scene can act as a proxy for inducing distance information of different objects in the scene, for the task of audio binauralization. We propose a novel encoder-decoder architecture with a hierarchical attention mechanism to encode image, depth and audio feature jointly. We design the network on top of state-of-the-art transformer networks for image and depth representation. We show empirically that the proposed method outperforms state-of-the-art methods comfortably for two challenging public datasets FAIR-Play and MUSIC-Stereo. We also demonstrate with qualitative results that the method is able to focus on the right information required for the task. The project details are available at \url{https://krantiparida.github.io/projects/bmonobinaural.html}

Kranti Kumar Parida, Siddharth Srivastava, Neeraj Matiyali et al.

Binaural audio gives the listener the feeling of being in the recording place and enhances the immersive experience if coupled with AR/VR. But the problem with binaural audio recording is that it requires a specialized setup which is not possible to fabricate within handheld devices as compared to traditional mono audio that can be recorded with a single microphone. In order to overcome this drawback, prior works have tried to uplift the mono recorded audio to binaural audio as a post processing step conditioning on the visual input. But all the prior approaches missed other most important information required for the task, i.e. distance of different sound producing objects from the recording setup. In this work, we argue that the depth map of the scene can act as a proxy for encoding distance information of objects in the scene and show that adding depth features along with image features improves the performance both qualitatively and quantitatively. We propose a novel encoder-decoder architecture, where we use a hierarchical attention mechanism to encode the image and depth feature extracted from individual transformer backbone, with audio features at each layer of the decoder.

Siddharth Srivastava, Gaurav Sharma

We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. As a first contribution, we propose to augment the vertex representations with important local geometric information of the points, followed by nonlinear projection using a MLP. As a second contribution, we propose to improve the graph construction for GNNs for 3D point clouds. The existing methods work with a k-nn based approach for constructing the local neighborhood graph. We argue that it might lead to reduction in coverage in case of dense sampling by sensors in some regions of the scene. The proposed methods aims to counter such problems and improve coverage in such cases. As the traditional GNNs were designed to work with general graphs, where vertices may have no geometric interpretations, we see both our proposals as augmenting the general graphs to incorporate the geometric nature of 3D point clouds. While being simple, we demonstrate with multiple challenging benchmarks, with relatively clean CAD models, as well as with real world noisy scans, that the proposed method achieves state of the art results on benchmarks for 3D classification (ModelNet40) , part segmentation (ShapeNet) and semantic segmentation (Stanford 3D Indoor Scenes Dataset). We also show that the proposed network achieves faster training convergence, i.e. ~40% less epochs for classification. The project details are available at https://siddharthsrivastava.github.io/publication/geomgcnn/

Kranti Kumar Parida, Gaurav Sharma

Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space. This shared space often also acts as a bridge for translating the modalities. We address the problem of learning such representation space by proposing and exploiting the property of Discriminative Semantic Transitive Consistency -- ensuring that the data points are correctly classified even after being transferred to the other modality. Along with semantic transitive consistency, we also enforce the traditional distance minimizing constraint which makes the projections of the corresponding data points from both the modalities to come closer in the representation space. We analyze and compare the contribution of both the loss terms and their interaction, for the task. In addition, we incorporate semantic cycle-consistency for each of the modality. We empirically demonstrate better performance owing to the different components with clear ablation studies. We also provide qualitative results to support the proposals.

Kranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

We address the problem of estimating depth with multi modal audio visual data. Inspired by the ability of animals, such as bats and dolphins, to infer distance of objects with echolocation, some recent methods have utilized echoes for depth estimation. We propose an end-to-end deep learning based pipeline utilizing RGB images, binaural echoes and estimated material properties of various objects within a scene. We argue that the relation between image, echoes and depth, for different scene elements, is greatly influenced by the properties of those elements, and a method designed to leverage this information can lead to significantly improved depth estimation from audio visual inputs. We propose a novel multi modal fusion technique, which incorporates the material properties explicitly while combining audio (echoes) and visual modalities to predict the scene depth. We show empirically, with experiments on Replica dataset, that the proposed method obtains 28% improvement in RMSE compared to the state-of-the-art audio-visual depth prediction method. To demonstrate the effectiveness of our method on larger dataset, we report competitive performance on Matterport3D, proposing to use it as a multimodal depth prediction benchmark with echoes for the first time. We also analyse the proposed method with exhaustive ablation experiments and qualitative results. The code and models are available at https://krantiparida.github.io/projects/bimgdepth.html

Xiangyun Zhao, Samuel Schulter, Gaurav Sharma et al.

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant application-relevant categories can be picked and merged form arbitrary existing datasets. However, naive merging of datasets is not possible in this case, due to inconsistent object annotations. Consider an object category like faces that is annotated in one dataset, but is not annotated in another dataset, although the object itself appears in the latter images. Some categories, like face here, would thus be considered foreground in one dataset, but background in another. To address this challenge, we design a framework which works with such partial annotations, and we exploit a pseudo labeling approach that we adapt for our specific case. We propose loss functions that carefully integrate partial but correct annotations with complementary but noisy pseudo labels. Evaluation in the proposed novel setting requires full annotation on the test set. We collect the required annotations and define a new challenging experimental setup for this task based one existing public datasets. We show improved performances compared to competitive baselines and appropriate adaptations of existing work.

Kranti Kumar Parida, Neeraj Matiyali, Tanaya Guha et al.

We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zeroshot classification and retrieval, when using multimodal extensions of embedding learning methods. We also propose a novel method to predict the `dominant' modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes.

Neeraj Matiyali, Gaurav Sharma

We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip based similarity is appropriate for the task. We show that using a learned clip similarity aggregation function allows filtering out hard clip pairs, e.g. where the person is not clearly visible, is in a challenging pose, or where the poses in the two clips are too different to be informative. This allows the method to focus on clip-pairs which are more informative for the task. We also introduce the use of 3D CNNs for video-based re-identification and show their effectiveness by performing equivalent to previous works, which use optical flow in addition to RGB, while using RGB inputs only. We give quantitative results on three challenging public benchmarks and show better or competitive performance. We also validate our method qualitatively.

Li Ding, Mohammad H. Bawany, Ajay E. Kuriyan et al.

While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus FA images. Binary vessels maps are first detected from CF images with a pre-trained neural network and then are geometrically registered with and transferred to FA images via robust parametric chamfer alignment to a preliminary FA vessel detection obtained with an unsupervised technique. Using the transferred vessels as initial ground truth labels for deep learning, the human-in-the-loop approach progressively improves the quality of the ground truth labeling by iterating between deep-learning and labeling. The approach significantly reduces manual labeling effort while increasing engagement. We highlight several important considerations for the proposed methodology and validate the performance on three datasets. Experimental results demonstrate that the proposed pipeline significantly reduces the annotation effort and the resulting deep learning methods outperform prior existing FA vessel detection methods by a significant margin. A new public dataset, RECOVERY-FA19, is introduced that includes high-resolution ultra-widefield images and accurately labeled ground truth binary vessel maps.

Siddharth Srivastava, Frederic Jurie, Gaurav Sharma

We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios. We propose to lift the 2D images to 3D representations using learned neural networks and leverage existing networks working directly on 3D data to perform 3D object detection and localization. We show that, with carefully designed training mechanism and automatically selected minimally noisy data, such a method is not only feasible, but gives higher results than many methods working on actual 3D inputs acquired from physical sensors. On the challenging KITTI benchmark, we show that our 2D to 3D lifted method outperforms many recent competitive 3D networks while significantly outperforming previous state-of-the-art for 3D detection from monocular images. We also show that a late fusion of the output of the network trained on generated 3D images, with that trained on real 3D images, improves performance. We find the results very interesting and argue that such a method could serve as a highly reliable backup in case of malfunction of expensive 3D sensors, if not potentially making them redundant, at least in the case of low human injury risk autonomous navigation scenarios like warehouse automation.

Ankan Bansal, Karan Sikka, Gaurav Sharma et al.

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification. We present a principled approach by first adapting visual-semantic embeddings for ZSD. We then discuss the problems associated with selecting a background class and motivate two background-aware approaches for learning robust detectors. One of these models uses a fixed background class and the other is based on iterative latent assignments. We also outline the challenge associated with using a limited number of training classes and propose a solution based on dense sampling of the semantic label space using auxiliary data with a large number of categories. We propose novel splits of two standard detection datasets - MSCOCO and VisualGenome, and present extensive empirical results in both the traditional and generalized zero-shot settings to highlight the benefits of the proposed methods. We provide useful insights into the algorithm and conclude by posing some open questions to encourage further research.

Samyak Datta, Gaurav Sharma, C. V. Jawahar

We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. We mine supervised training data by noting that multiple faces in the same video frame must belong to different persons and the same face tracked across multiple frames must belong to the same person. We obtain millions of face pairs from hundreds of videos without using any manual supervision. Although faces extracted from videos have a lower spatial resolution than those which are available as part of standard supervised face datasets such as LFW and CASIA-WebFace, the former represent a much more realistic setting, e.g. in surveillance scenarios where most of the faces detected are very small. We train our CNNs with the relatively low resolution faces extracted from video frames collected, and achieve a higher verification accuracy on the benchmark LFW dataset cf. hand-crafted features such as LBPs, and even surpasses the performance of state-of-the-art deep networks such as VGG-Face, when they are made to work with low resolution input images.

Shubham Gupta, Gaurav Sharma, Ambedkar Dukkipati

Networks observed in real world like social networks, collaboration networks etc., exhibit temporal dynamics, i.e. nodes and edges appear and/or disappear over time. In this paper, we propose a generative, latent space based, statistical model for such networks (called dynamic networks). We consider the case where the number of nodes is fixed, but the presence of edges can vary over time. Our model allows the number of communities in the network to be different at different time steps. We use a neural network based methodology to perform approximate inference in the proposed model and its simplified version. Experiments done on synthetic and real world networks for the task of community detection and link prediction demonstrate the utility and effectiveness of our model as compared to other similar existing approaches.

Ahmed Elliethy, Gaurav Sharma

Vehicle tracking in Wide Area Motion Imagery (WAMI) relies on associating vehicle detections across multiple WAMI frames to form tracks corresponding to individual vehicles. The temporal window length, i.e., the number $M$ of sequential frames, over which associations are collectively estimated poses a trade-off between accuracy and computational complexity. A larger $M$ improves performance because the increased temporal context enables the use of motion models and allows occlusions and spurious detections to be handled better. The number of total hypotheses tracks, on the other hand, grows exponentially with increasing $M$, making larger values of $M$ computationally challenging to tackle. In this paper, we introduce SPAAM an iterative approach that progressively grows $M$ with each iteration to improve estimated tracks by exploiting the enlarged temporal context while keeping computation manageable through two novel approaches for pruning association hypotheses. First, guided by a road network, accurately co-registered to the WAMI frames, we disregard unlikely associations that do not agree with the road network. Second, as $M$ is progressively enlarged at each iteration, the related increase in association hypotheses is limited by revisiting only the subset of association possibilities rendered open by stochastically determined dis-associations for the previous iteration. The stochastic dis-association at each iteration maintains each estimated association according to an estimated probability for confidence, obtained via a probabilistic model. Associations at each iteration are then estimated globally over the $M$ frames by (approximately) solving a binary integer programming problem for selecting a set of compatible tracks. Vehicle tracking results obtained over test WAMI datasets indicate that our proposed approach provides significant performance improvements over 3 alternatives.

Rahul Sharma, Tanaya Guha, Gaurav Sharma

Public speaking is an important aspect of human communication and interaction. The majority of computational work on public speaking concentrates on analyzing the spoken content, and the verbal behavior of the speakers. While the success of public speaking largely depends on the content of the talk, and the verbal behavior, non-verbal (visual) cues, such as gestures and physical appearance also play a significant role. This paper investigates the importance of visual cues by estimating their contribution towards predicting the popularity of a public lecture. For this purpose, we constructed a large database of more than $1800$ TED talk videos. As a measure of popularity of the TED talks, we leverage the corresponding (online) viewers' ratings from YouTube. Visual cues related to facial and physical appearance, facial expressions, and pose variations are extracted from the video frames using convolutional neural network (CNN) models. Thereafter, an attention-based long short-term memory (LSTM) network is proposed to predict the video popularity from the sequence of visual features. The proposed network achieves state-of-the-art prediction accuracy indicating that visual cues alone contain highly predictive information about the popularity of a talk. Furthermore, our network learns a human-like attention mechanism, which is particularly useful for interpretability, i.e. how attention varies with time, and across different visual cues by indicating their relative importance.

Santhosh K. Ramakrishnan, Ambar Pal, Gaurav Sharma et al.

We study the problem of answering questions about images in the harder setting, where the test questions and corresponding images contain novel objects, which were not queried about in the training data. Such setting is inevitable in real world-owing to the heavy tailed distribution of the visual categories, there would be some objects which would not be annotated in the train set. We show that the performance of two popular existing methods drop significantly (up to 28%) when evaluated on novel objects cf. known objects. We propose methods which use large existing external corpora of (i) unlabeled text, i.e. books, and (ii) images tagged with classes, to achieve novel object based visual question answering. We do systematic empirical studies, for both an oracle case where the novel objects are known textually, as well as a fully automatic case without any explicit knowledge of the novel objects, but with the minimal assumption that the novel objects are semantically related to the existing objects in training. The proposed methods for novel object based visual question answering are modular and can potentially be used with many visual question answering architectures. We show consistent improvements with the two popular architectures and give qualitative analysis of the cases where the model does well and of those where it fails to bring improvements.

Siddharth Srivastava, Gaurav Sharma, Brejesh Lall

We present a method for discovering never-seen-before objects in 3D point clouds obtained from sensors like Microsoft Kinect. We generate supervoxels directly from the point cloud data and use them with a Siamese network, built on a recently proposed 3D convolutional neural network architecture. We use known objects to train a non-linear embedding of supervoxels, by optimizing the criteria that supervoxels which fall on the same object should be closer than those which fall on different objects, in the embedding space. We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery. We validate the method with extensive experiments, quantitatively showing that it can discover numerous unseen objects while being trained on only a few dense 3D models. We also show very good qualitative results of object discovery in point cloud data when the test objects, either specific instances or even categories, were never seen during training.

Bochen Li, Xinzhao Liu, Karthik Dinesh et al.

We introduce a dataset for facilitating audio-visual analysis of music performances. The dataset comprises 44 simple multi-instrument classical music pieces assembled from coordinated but separately recorded performances of individual tracks. For each piece, we provide the musical score in MIDI format, the audio recordings of the individual tracks, the audio and video recording of the assembled mixture, and ground-truth annotation files including frame-level and note-level transcriptions. We describe our methodology for the creation of the dataset, particularly highlighting our approaches for addressing the challenges involved in maintaining synchronization and expressiveness. We demonstrate the high quality of synchronization achieved with our proposed approach by comparing the dataset with existing widely-used music audio datasets. We anticipate that the dataset will be useful for the development and evaluation of existing music information retrieval (MIR) tasks, as well as for novel multi-modal tasks. We benchmark two existing MIR tasks (multi-pitch analysis and score-informed source separation) on the dataset and compare with other existing music audio datasets. Additionally, we consider two novel multi-modal MIR tasks (visually informed multi-pitch analysis and polyphonic vibrato analysis) enabled by the dataset and provide evaluation measures and baseline systems for future comparisons (from our recent work). Finally, we propose several emerging research directions that the dataset enables.

Amlan Kar, Nishant Rai, Karan Sikka et al.

We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient information to discriminate an action class present in a video, from the rest. The proposed method learns to pool such discriminative and informative frames, while discarding a majority of the non-informative frames in a single temporal scan of the video. Our algorithm does so by continuously predicting the discriminative importance of each video frame and subsequently pooling them in a deep learning framework. We show the effectiveness of our proposed pooling method on standard benchmarks where it consistently improves on baseline pooling methods, with both RGB and optical flow based Convolutional networks. Further, in combination with complementary video representations, we show results that are competitive with respect to the state-of-the-art results on two challenging and publicly available benchmark datasets.

Binod Bhattarai, Gaurav Sharma, Frederic Jurie

Facial analysis is a key technology for enabling human-machine interaction. In this context, we present a client-server framework, where a client transmits the signature of a face to be analyzed to the server, and, in return, the server sends back various information describing the face e.g. is the person male or female, is she/he bald, does he have a mustache, etc. We assume that a client can compute one (or a combination) of visual features; from very simple and efficient features, like Local Binary Patterns, to more complex and computationally heavy, like Fisher Vectors and CNN based, depending on the computing resources available. The challenge addressed in this paper is to design a common universal representation such that a single merged signature is transmitted to the server, whatever be the type and number of features computed by the client, ensuring nonetheless an optimal performance. Our solution is based on learning of a common optimal subspace for aligning the different face features and merging them into a universal signature. We have validated the proposed method on the challenging CelebA dataset, on which our method outperforms existing state-of-the-art methods when rich representation is available at test time, while giving competitive performance when only simple signatures (like LBP) are available at test time due to resource constraints on the client.

Karan Sikka, Gaurav Sharma

We study the problem of video classification for facial analysis and human action recognition. We propose a novel weakly supervised learning method that models the video as a sequence of automatically mined, discriminative sub-events (eg. onset and offset phase for "smile", running and jumping for "highjump"). The proposed model is inspired by the recent works on Multiple Instance Learning and latent SVM/HCRF -- it extends such frameworks to model the ordinal aspect in the videos, approximately. We obtain consistent improvements over relevant competitive baselines on four challenging and publicly available video based facial analysis datasets for prediction of expression, clinical pain and intent in dyadic conversations and on three challenging human action datasets. We also validate the method with qualitative results and show that they largely support the intuitions behind the method.

Binod Bhattarai, Gaurav Sharma, Frederic Jurie

We propose a novel Coupled Projection multi-task Metric Learning (CP-mtML) method for large scale face retrieval. In contrast to previous works which were limited to low dimensional features and small datasets, the proposed method scales to large datasets with high dimensional face descriptors. It utilises pairwise (dis-)similarity constraints as supervision and hence does not require exhaustive class annotation for every training image. While, traditionally, multi-task learning methods have been validated on same dataset but different tasks, we work on the more challenging setting with heterogeneous datasets and different tasks. We show empirical validation on multiple face image datasets of different facial traits, e.g. identity, age and expression. We use classic Local Binary Pattern (LBP) descriptors along with the recent Deep Convolutional Neural Network (CNN) features. The experiments clearly demonstrate the scalability and improved performance of the proposed method on the tasks of identity and age based face image retrieval compared to competitive existing methods, on the standard datasets and with the presence of a million distractor face images.

Karan Sikka, Gaurav Sharma, Marian Bartlett

We study the problem of facial analysis in videos. We propose a novel weakly supervised learning method that models the video event (expression, pain etc.) as a sequence of automatically mined, discriminative sub-events (eg. onset and offset phase for smile, brow lower and cheek raise for pain). The proposed model is inspired by the recent works on Multiple Instance Learning and latent SVM/HCRF- it extends such frameworks to model the ordinal or temporal aspect in the videos, approximately. We obtain consistent improvements over relevant competitive baselines on four challenging and publicly available video based facial analysis datasets for prediction of expression, clinical pain and intent in dyadic conversations. In combination with complimentary features, we report state-of-the-art results on these datasets.

Yongqin Xian, Zeynep Akata, Gaurav Sharma et al.

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model by incorporating latent variables. Instead of learning a single bilinear map, it learns a collection of maps with the selection, of which map to use, being a latent variable for the current image-class pair. We train the model with a ranking based objective function which penalizes incorrect rankings of the true class for a given image. We empirically demonstrate that our model improves the state-of-the-art for various class embeddings consistently on three challenging publicly available datasets for the zero-shot setting. Moreover, our method leads to visually highly interpretable results with clear clusters of different fine-grained object properties that correspond to different latent variable maps.

Gaurav Sharma, Frederic Jurie

We propose a new image representation for texture categorization and facial analysis, relying on the use of higher-order local differential statistics as features. It has been recently shown that small local pixel pattern distributions can be highly discriminative while being extremely efficient to compute, which is in contrast to the models based on the global structure of images. Motivated by such works, we propose to use higher-order statistics of local non-binarized pixel patterns for the image description. The proposed model does not require either (i) user specified quantization of the space (of pixel patterns) or (ii) any heuristics for discarding low occupancy volumes of the space. We propose to use a data driven soft quantization of the space, with parametric mixture models, combined with higher-order statistics, based on Fisher scores. We demonstrate that this leads to a more expressive representation which, when combined with discriminatively learned classifiers and metrics, achieves state-of-the-art performance on challenging texture and facial analysis datasets, in low complexity setup. Further, it is complementary to higher complexity features and when combined with them improves performance.

Gaurav Sharma, Bernt Schiele

We propose a novel algorithm for the task of supervised discriminative distance learning by nonlinearly embedding vectors into a low dimensional Euclidean space. We work in the challenging setting where supervision is with constraints on similar and dissimilar pairs while training. The proposed method is derived by an approximate kernelization of a linear Mahalanobis-like distance metric learning algorithm and can also be seen as a kernel neural network. The number of model parameters and test time evaluation complexity of the proposed method are O(dD) where D is the dimensionality of the input features and d is the dimension of the projection space - this is in contrast to the usual kernelization methods as, unlike them, the complexity does not scale linearly with the number of training examples. We propose a stochastic gradient based learning algorithm which makes the method scalable (w.r.t. the number of training examples), while being nonlinear. We train the method with up to half a million training pairs of 4096 dimensional CNN features. We give empirical comparisons with relevant baselines on seven challenging datasets for the task of low dimensional semantic category based image retrieval.

Gaurav Sharma, Frederic Jurie, Cordelia Schmid

We introduce an Expanded Parts Model (EPM) for recognizing human attributes (e.g. young, short hair, wearing suit) and actions (e.g. running, jumping) in still images. An EPM is a collection of part templates which are learnt discriminatively to explain specific scale-space regions in the images (in human centric coordinates). This is in contrast to current models which consist of a relatively few (i.e. a mixture of) 'average' templates. EPM uses only a subset of the parts to score an image and scores the image sparsely in space, i.e. it ignores redundant and random background in an image. To learn our model, we propose an algorithm which automatically mines parts and learns corresponding discriminative templates together with their respective locations from a large number of candidate parts. We validate our method on three recent challenging datasets of human attributes and actions. We obtain convincing qualitative and state-of-the-art quantitative results on the three datasets.