arXiv subjects

Aniket Bera

Publications and source records attributed to Aniket Bera.

At least 91 records · Page 5Linked to original sources

arXiv2023

DF-TransFusion: Multimodal Deepfake Detection via Lip-Audio Cross-Attention and Facial Self-Attention

With the rise in manipulated media, deepfake detection has become an imperative task for preserving the authenticity of digital content. In this paper, we present a novel multi-modal audio-video framework designed to concurrently process audio and video inputs for deepfake detection tasks. Our model capitalizes on lip synchronization with input audio through a cross-attention mechanism while extracting visual cues via a fine-tuned VGG-16 network. Subsequently, a transformer encoder network is employed to perform facial self-attention. We conduct multiple ablation studies highlighting different strengths of our approach. Our multi-modal methodology outperforms state-of-the-art multi-modal deepfake detection techniques in terms of F-1 and per-video AUC scores.

cs.CV↗

arXiv2023

AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis

Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and subtle differences in the same emotion. The quantized emotional embeddings are implicitly derived from spoken speech samples, eliminating the need for one-hot vectors or explicit strength embeddings. Experimental results demonstrate the effectiveness of our approach in controlling the emotions of generated speech while preserving identity, style, and emotional cadence unique to each speaker. We showcase the language-independent emotion modeling capability of the quantized emotional embeddings learned from a bilingual (English and Chinese) speech corpus with an emotion transfer task from a reference speech to a target speech. We achieve state-of-art results on both qualitative and quantitative metrics.

cs.SD↗

arXiv2023

RAIST: Learning Risk Aware Traffic Interactions via Spatio-Temporal Graph Convolutional Networks

A key aspect of driving a road vehicle is to interact with other road users, assess their intentions and make risk-aware tactical decisions. An intuitive approach to enabling an intelligent automated driving system would be incorporating some aspects of human driving behavior. To this end, we propose a novel driving framework for egocentric views based on spatio-temporal traffic graphs. The traffic graphs model not only the spatial interactions amongst the road users but also their individual intentions through temporally associated message passing. We leverage a spatio-temporal graph convolutional network (ST-GCN) to train the graph edges. These edges are formulated using parameterized functions of 3D positions and scene-aware appearance features of road agents. Along with tactical behavior prediction, it is crucial to evaluate the risk-assessing ability of the proposed framework. We claim that our framework learns risk-aware representations by improving on the task of risk object identification, especially in identifying objects with vulnerable interactions like pedestrians and cyclists.

cs.CV↗

arXiv2023

SG-LSTM: Social Group LSTM for Robot Navigation Through Dense Crowds

With the increasing availability and affordability of personal robots, they will no longer be confined to large corporate warehouses or factories but will instead be expected to operate in less controlled environments alongside larger groups of people. In addition to ensuring safety and efficiency, it is crucial to minimize any negative psychological impact robots may have on humans and follow unwritten social norms in these situations. Our research aims to develop a model that can predict the movements of pedestrians and perceptually-social groups in crowded environments. We introduce a new Social Group Long Short-term Memory (SG-LSTM) model that models human groups and interactions in dense environments using a socially-aware LSTM to produce more accurate trajectory predictions. Our approach enables navigation algorithms to calculate collision-free paths faster and more accurately in crowded environments. Additionally, we also release a large video dataset with labeled pedestrian groups for the broader social navigation community. We show comparisons with different metrics on different datasets (ETH, Hotel, MOT15) and different prediction approaches (LIN, LSTM, O-LSTM, S-LSTM) as well as runtime performance.

cs.RO↗

arXiv2023

DroNeRF: Real-time Multi-agent Drone Pose Optimization for Computing Neural Radiance Fields

We present a novel optimization algorithm called DroNeRF for the autonomous positioning of monocular camera drones around an object for real-time 3D reconstruction using only a few images. Neural Radiance Fields or NeRF, is a novel view synthesis technique used to generate new views of an object or scene from a set of input images. Using drones in conjunction with NeRF provides a unique and dynamic way to generate novel views of a scene, especially with limited scene capabilities of restricted movements. Our approach focuses on calculating optimized pose for individual drones while solely depending on the object geometry without using any external localization system. The unique camera positioning during the data-capturing phase significantly impacts the quality of the 3D model. To evaluate the quality of our generated novel views, we compute different perceptual metrics like the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure(SSIM). Our work demonstrates the benefit of using an optimal placement of various drones with limited mobility to generate perceptually better results.

cs.RO↗

arXiv2023

ARC: Alignment-based Redirection Controller for Redirected Walking in Complex Environments

We present a novel redirected walking controller based on alignment that allows the user to explore large and complex virtual environments, while minimizing the number of collisions with obstacles in the physical environment. Our alignment-based redirection controller, ARC, steers the user such that their proximity to obstacles in the physical environment matches the proximity to obstacles in the virtual environment as closely as possible. To quantify a controller's performance in complex environments, we introduce a new metric, Complexity Ratio (CR), to measure the relative environment complexity and characterize the difference in navigational complexity between the physical and virtual environments. Through extensive simulation-based experiments, we show that ARC significantly outperforms current state-of-the-art controllers in its ability to steer the user on a collision-free path. We also show through quantitative and qualitative measures of performance that our controller is robust in complex environments with many obstacles. Our method is applicable to arbitrary environments and operates without any user input or parameter tweaking, aside from the layout of the environments. We have implemented our algorithm on the Oculus Quest head-mounted display and evaluated its performance in environments with varying complexity. Our project website is available at https://gamma.umd.edu/arc/.

cs.GR↗

arXiv2023

ENI: Quantifying Environment Compatibility for Natural Walking in Virtual Reality

We present a novel metric to analyze the similarity between the physical environment and the virtual environment for natural walking in virtual reality. Our approach is general and can be applied to any pair of physical and virtual environments. We use geometric techniques based on conforming constrained Delaunay triangulations and visibility polygons to compute the Environment Navigation Incompatibility (ENI) metric that can be used to measure the complexity of performing simultaneous navigation. We demonstrate applications of ENI for highlighting regions of incompatibility for a pair of environments, guiding the design of the virtual environments to make them more compatible with a fixed physical environment, and evaluating the performance of different redirected walking controllers. We validate the ENI metric using simulations and two user studies. Results of our simulations and user studies show that in the environment pair that our metric identified as more navigable, users were able to walk for longer before colliding with objects in the physical environment. Overall, ENI is the first general metric that can automatically identify regions of high and low compatibility in physical and virtual environments. Our project website is available at https://gamma.umd.edu/eni/.

cs.GR↗

arXiv2023

AdaFNIO: Adaptive Fourier Neural Interpolation Operator for video frame interpolation

We present, AdaFNIO - Adaptive Fourier Neural Interpolation Operator, a neural operator-based architecture to perform video frame interpolation. Current deep learning based methods rely on local convolutions for feature learning and suffer from not being scale-invariant, thus requiring training data to be augmented through random flipping and re-scaling. On the other hand, AdaFNIO, learns the features in the frames, independent of input resolution, through token mixing and global convolution in the Fourier space or the spectral domain by using Fast Fourier Transform (FFT). We show that AdaFNIO can produce visually smooth and accurate results. To evaluate the visual quality of our interpolated frames, we calculate the structural similarity index (SSIM) and Peak Signal to Noise Ratio (PSNR) between the generated frame and the ground truth frame. We provide the quantitative performance of our model on Vimeo-90K dataset, DAVIS, UCF101 and DISFA+ dataset.

cs.CV↗

arXiv2023

SeekNet: Improved Human Instance Segmentation and Tracking via Reinforcement Learning Based Optimized Robot Relocation

Amodal recognition is the ability of the system to detect occluded objects. Most SOTA Visual Recognition systems lack the ability to perform amodal recognition. Few studies have achieved amodal recognition through passive prediction or embodied recognition approaches. However, these approaches suffer from challenges in real-world applications, such as dynamic obstacles. We propose SeekNet, an improved optimization method for amodal recognition through embodied visual recognition. Additionally, we implement SeekNet for social robots, where there are multiple interactions with crowded pedestrians. We also demonstrate the benefits of our algorithm on occluded human detection and tracking over other baselines. Additionally, we set up a multi-robot environment with SeekNet to identify and track visual disease markers for airborne disease in crowded areas. We conduct our experiments in a simulated indoor environment and show that our method enhances the overall accuracy of the amodal recognition task and achieves the largest improvement in detection accuracy over time in comparison to the baseline approaches.

cs.CV↗

arXiv2023

EWareNet: Emotion Aware Human Intent Prediction and Adaptive Spatial Profile Fusion for Social Robot Navigation

We present EWareNet, a novel intent and affect-aware social robot navigation algorithm among pedestrians. Our approach predicts the trajectory-based pedestrian intent from gait sequence, which is then used for intent-guided navigation taking into account social and proxemic constraints. We propose a transformer-based model that works on commodity RGB-D cameras mounted onto a moving robot. Our intent prediction routine is integrated into a mapless navigation scheme and makes no assumptions about the environment of pedestrian motion. Our navigation scheme consists of a novel obstacle profile representation methodology that is dynamically adjusted based on the pedestrian pose, intent, and affect. The navigation scheme is based on a reinforcement learning algorithm that takes pedestrian intent and robot's impact on pedestrian intent into consideration, in addition to the environmental configuration. We outperform current state-of-art algorithms for intent prediction from 3D gaits.

cs.RO↗

arXiv2023

AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning

We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to automatically identify the human target and scale it appropriately. This makes it easier to extract the key features and reduces the computational overhead. We also present an efficient temporal reasoning algorithm to capture the action information along the spatial and temporal domains within a controllable computational cost. Our approach has been implemented and evaluated both on the desktop with high-end GPUs and on the low power Robotics RB5 Platform for robots and drones. In practice, we achieve 6.1-7.4% improvement over SOTA in Top-1 accuracy on the RoCoG-v2 dataset, 8.3-10.4% improvement on the UAV-Human dataset and 3.2% improvement on the Drone Action dataset.

cs.CV↗

arXiv2023

Developing an Effective and Automated Patient Engagement Estimator for Telehealth: A Machine Learning Approach

We discuss MET, a learning-based algorithm proposed for perceiving a patient's level of engagement during telehealth sessions. We leverage latent vectors corresponding to Affective and Cognitive features frequently used in psychology literature to understand a person's level of engagement in a semi-supervised GAN-based framework. We showcase the efficacy of this method from the perspective of mental health and more specifically how this can be leveraged for a better understanding of patient engagement during telemental health sessions. To further the development of similar technologies that can be useful for telehealth, we also plan to release a dataset MEDICA containing 1299 video clips, each 3 seconds long and show experiments on the same. Our framework reports a 40% improvement in RMSE (Root Mean Squared Error) over state-of-the-art methods for engagement estimation. In our real-world tests, we also observed positive correlations between the working alliance inventory scores reported by psychotherapists. This indicates the potential of the proposed model to present patient engagement estimations that aligns well with the engagement measures used by psychotherapists.

cs.CV↗

arXiv2022

PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators

We address the problem of generating 3D human motions in dyadic activities. In contrast to the concurrent works, which mainly focus on generating the motion of a single actor from the textual description, we generate the motion of one of the actors from the motion of the other participating actor in the action. This is a particularly challenging, under-explored problem, that requires learning intricate relationships between the motion of two actors participating in an action and also identifying the action from the motion of one actor. To address these, we propose partner conditioned motion operator (PaCMO), a neural operator-based generative model which learns the distribution of human motion conditioned by the partner's motion in function spaces through adversarial training. Our model can handle long unlabeled action sequences at arbitrary time resolution. We also introduce the "Functional Frechet Inception Distance" ($F^2ID$) metric for capturing similarity between real and generated data for function spaces. We test PaCMO on NTU RGB+D and DuetDance datasets and our model produces realistic results evidenced by the $F^2ID$ score and the conducted user study.

cs.CV↗

arXiv2022

Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes

We present a novel method for placing a 3D human animation into a 3D scene while maintaining any human-scene interactions in the animation. We use the notion of computing the most important meshes in the animation for the interaction with the scene, which we call "keyframes." These keyframes allow us to better optimize the placement of the animation into the scene such that interactions in the animations (standing, laying, sitting, etc.) match the affordances of the scene (e.g., standing on the floor or laying in a bed). We compare our method, which we call PAAK, with prior approaches, including POSA, PROX ground truth, and a motion synthesis method, and highlight the benefits of our method with a perceptual study. Human raters preferred our PAAK method over the PROX ground truth data 64.6\% of the time. Additionally, in direct comparisons, the raters preferred PAAK over competing methods including 61.5\% compared to POSA.

cs.CV↗

arXiv2022

Estimating Emotion Contagion on Social Media via Localized Diffusion in Dynamic Graphs

We present a computational approach for estimating emotion contagion on social media networks. Built on a foundation of psychology literature, our approach estimates the degree to which the perceivers' emotional states (positive or negative) start to match those of the expressors, based on the latter's content. We use a combination of deep learning and social network analysis to model emotion contagion as a diffusion process in dynamic social network graphs, taking into consideration key aspects like causality, homophily, and interference. We evaluate our approach on user behavior data obtained from a popular social media platform for sharing short videos. We analyze the behavior of 48 users over a span of 8 weeks (over 200k audio-visual short posts analyzed) and estimate how contagious the users with whom they engage with are on social media. As per the theory of diffusion, we account for the videos a user watches during this time (inflow) and the daily engagements; liking, sharing, downloading or creating new videos (outflow) to estimate contagion. To validate our approach and analysis, we obtain human feedback on these 48 social media platform users with an online study by collecting responses of about 150 participants. We report users who interact with more number of creators on the platform are 12% less prone to contagion, and those who consume more content of `negative' sentiment are 23% more prone to contagion. We will publicly release our code upon acceptance.

cs.SI↗

arXiv2022

3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos

We present 3MASSIV, a multilingual, multimodal and multi-aspect, expertly-annotated dataset of diverse short videos extracted from short-video social media platform - Moj. 3MASSIV comprises of 50k short videos (20 seconds average duration) and 100K unlabeled videos in 11 different languages and captures popular short video trends like pranks, fails, romance, comedy expressed via unique audio-visual formats like self-shot videos, reaction videos, lip-synching, self-sung songs, etc. 3MASSIV presents an opportunity for multimodal and multilingual semantic understanding on these unique videos by annotating them for concepts, affective states, media types, and audio language. We present a thorough analysis of 3MASSIV and highlight the variety and unique aspects of our dataset compared to other contemporary popular datasets with strong baselines. We also show how the social media content in 3MASSIV is dynamic and temporal in nature, which can be used for semantic understanding tasks and cross-lingual analysis.

cs.CV↗

arXiv2021

Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders

We present a novel generalized zero-shot algorithm to recognize perceived emotions from gestures. Our task is to map gestures to novel emotion categories not encountered in training. We introduce an adversarial, autoencoder-based representation learning that correlates 3D motion-captured gesture sequence with the vectorized representation of the natural-language perceived emotion terms using word2vec embeddings. The language-semantic embedding provides a representation of the emotion label space, and we leverage this underlying distribution to map the gesture-sequences to the appropriate categorical emotion labels. We train our method using a combination of gestures annotated with known emotion terms and gestures not annotated with any emotions. We evaluate our method on the MPI Emotional Body Expressions Database (EBEDB) and obtain an accuracy of $58.43\%$. This improves the performance of current state-of-the-art algorithms for generalized zero-shot learning by $25$--$27\%$ on the absolute.

cs.CV↗

arXiv2021

Redirected Walking in Static and Dynamic Scenes Using Visibility Polygons

We present a new approach for redirected walking in static and dynamic scenes that uses techniques from robot motion planning to compute the redirection gains that steer the user on collision-free paths in the physical space. Our first contribution is a mathematical framework for redirected walking using concepts from motion planning and configuration spaces. This framework highlights various geometric and perceptual constraints that tend to make collision-free redirected walking difficult. We use our framework to propose an efficient solution to the redirection problem that uses the notion of visibility polygons to compute the free spaces in the physical environment and the virtual environment. The visibility polygon provides a concise representation of the entire space that is visible, and therefore walkable, to the user from their position within an environment. Using this representation of walkable space, we apply redirected walking to steer the user to regions of the visibility polygon in the physical environment that closely match the region that the user occupies in the visibility polygon in the virtual environment. We show that our algorithm is able to steer the user along paths that result in significantly fewer resets than existing state-of-the-art algorithms in both static and dynamic scenes. Our project website is available at https://gamma.umd.edu/vis_poly/.

cs.RO↗