Abstract

Visual servoing has been gaining popularity in various real-world vision-centric robotic applications. Autonomous robotic grasping often deals with unseen and unstructured environments, and in this task, Visual Servoing has been able to generate improved end-effector control by providing visual feedback. However, existing Servoing-aided grasping methods tend to fail at the task of grasping in dynamic environments i.e. - moving objects. In this paper, we introduce DynGraspVS, a novel Image-based Visual Servoing-aided Grasping approach that models the motion of moving objects in its interaction matrix. Leveraging a single-step rollout strategy, our approach achieves a remarkable increase in success rate, while converging faster and achieving a smoother trajectory, while maintaining precise alignments in six degrees of freedom. By integrating the velocity information into the interaction matrix, our method is able to successfully complete the challenging task of robotic grasping in the case of dynamic objects, while outperforming existing deep Model Predictive Control (MPC) based methods in the PyBullet simulation environment. We test it with a range of objects in the YCB dataset with varying range of shapes, sizes, and material properties. We report various evaluation metrics such as photometric error, success rate, time taken, and trajectory length.

Abstract

In this paper, we introduce a novel approach to address the task of synthesizing speech from silent videos of any in-the-wild speaker solely based on lip movements. The traditional approach of directly generating speech from lip videos faces the challenge of not being able to learn a robust language model from speech alone, resulting in unsatisfactory outcomes. To overcome this issue, we propose incorporating noisy text supervision using a state-of-the-art lip-to-text network that instills language information into our model. The noisy text is generated using a pre-trained lip-to-text model, enabling our approach to work without text annotations during inference. We design a visual text-to-speech network that utilizes the visual stream to generate accurate speech, which is in-sync with the silent input video. We perform extensive experiments and ablation studies, demonstrating our approach's superiority over the current state-of-the-art methods on various benchmark datasets. Further, we demonstrate an essential practical application of our method in assistive technology by generating speech for an ALS patient who has lost the voice but can make mouth movements. Our demo video, code, and additional details can be found at http://cvit.iiit.ac.in/research/projects/cvit-projects/ms-l2s-itw.

Abstract

Emergency signages are crucial for safe evacuations but have been challenged by inconsistent and ambiguous designs. We conducted two experiments to evaluate a specific emergency signage design, i.e., running man's pictogram, in ease of conveying the direction to exit an unknown building. We compared the running man's pictogram with traditional arrow signage in exp.1, and in exp. 2, we examined the key features that contribute to the running man's composition. In both conditions, the participant's task was to determine the running man's/ arrow's orientation and press the instructed corresponding keys. We observed a faster and more accurate response for the right arrow than the right running man in experiment 1. Further, in exp. 2, the head/face component showed an advantage in identifying the running man's orientation over the leg/hand. Results suggest running man alone in emergency signage may be risky, especially when it is incomplete without a head and face.

Abstract

The control system design specifications for dynamical systems are typically provided in terms of the desired transient response and steady-state response. Meeting such requirements for dynamical systems whose mathematical models are unavailable is a challenging task. In this paper, we propose a learning-based controller to achieve the desired control system design specifications for unknown dynamical systems. We consider a SoTA model-free reinforcement learning agent (TD3) in the continuous state and action space setting where the agent has no knowledge of system dynamics. The selection of an appropriate reward function is a key factor that shapes the response of the dynamical system when the learning-based controller is implemented. The resulting controller is trained and tested for first-order and second-order linear systems, as well as a nonlinear system. The resulting trajectories of the closed-loop systems indicate that the transient and steady-state response can be altered by choosing the appropriate reward function while adhering to the constraints imposed on the control input.

Abstract

Stuttering is a speech disorder that affects speech fluency and rhythm, with millions worldwide experiencing it. Early diagnosis and treatment can significantly improve speech fluency and the quality of life for individuals who stutter. Automatic detection of stuttering events can help diagnose, monitor, and develop effective interventions. Therefore, this paper aims to propose a feature space-based classifier for detecting stuttering events in speech. To achieve this, we have investigated Zero Time Windowing Cepstral Coefficients (ZTWCC) as a feature set for stutter detection using classifiers such as SVM, LSTM, and Bidirectional LSTM. We compared the performance of ZTWCC with the standard handcrafted features, such as MFCC, CQCC, and SFFCC, on the SEP- 28K dataset with and without including phase information. The results in both cases indicate that ZTWCC is giving a higher F-1 score than baseline MFCC features.

Abstract

Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage. In this paper, we present a self-training based source-free video domain adaptation approach to address this challenge by bridging the gap between the source and the target domains. We use the source pre-trained model to generate pseudo-labels for the target domain samples, which are inevitably noisy. Thus, we treat the problem of source-free video domain adaptation as learning from noisy labels and argue that the samples with correct pseudo-labels can help us in adaptation. To this end, we leverage the crossentropy loss as an indicator of the correctness of the pseudo-labels and use the resulting small-loss samples from the target domain for fine-tuning the model. We further enhance the adaptation performance by implementing a teacher-student framework, in which the teacher, which is updated gradually, produces reliable pseudo-labels. Meanwhile, the student undergoes fine-tuning on the target domain videos using these generated pseudo-labels to improve its performance. Extensive experimental evaluations show that our methods, termed as CleanAdapt, CleanAdapt + TS, achieve state-of-the-art results, outperforming the existing approaches on various open datasets. Our source code is publicly available at https://avijit9.github.io/CleanAdapt.

Abstract

Language learning involves the correct acquisition of grammar skills. To facilitate learning with computer-assisted systems, automatic spoken grammatical error detection (SGED) is necessary. This work explores Automatic Speech Recognition (ASR), which decodes text from speech, for SGED. With current advancements in ASR technology, often it can be believed that these systems could capture spoken grammatical errors in the decoded text. However, these systems have an inherent bias from the language model towards the grammatically correct text. We explore the ASR-decoded text from commercially available current state-of-the-art systems considering a text-based GED algorithm and also its word-level confidence score (CS) for SGED. We perform the experiments on the spoken English data collected in-house from 13 subjects speaking 4110 grammatically erroneous and correct sentences. We found the highest relative improvement in SGED with CS is 15.36% compared to that with decoded text plus GED.

Abstract

Direct lighting from many area light sources is challenging due to variance from both choosing an important light and then a point on it. Resampled Importance Sampling (RIS) achieves low variance in such situations. However, it is limited to simple sampling strategies for its candidates. Specifically for area lights, we can improve the convergence of RIS by incorporating a better sampling strategy: Projected Solid Angle Sampling (ProjLTC). Naively combining RIS and ProjLTC improves equal sample convergence. However, it achieves little to no gain in equal time. We identify the core issue for the high run times and reformulate RIS for better integration with ProjLTC. Our method achieves better convergence and results in both equal sample and equal time. We evaluate our method on challenging scenes with varying numbers of area light sources and compare it to uniform sampling, RIS, and ProjLTC. In all cases, our method seldom performs worse than RIS and often performs better

Abstract

Students need to understand the assessment of requirements correctness while building software systems. It helps produce products that meet the stakeholder objectives. This poster illustrates an experiment conducted as a tool-based collaborative assignment for assessing the correctness of software products using a Virtual Reality (VR) application as part of a CS300-level course at our University.

Abstract

Large language models (LLMs) and generative AI have emerged as the most important areas in the field of natural language processing (NLP). LLMs are considered to be a key component in several NLP tasks, such as summarization, question-answering, sentiment classification, and translation. Newer LLMs, such as Chat- GPT, BLOOMZ, and several such variants, are known to train on multilingual training data and hence are expected to process and generate text in multiple languages. Considering the widespread use of LLMs, evaluating their efficacy in multilingual settings is imperative. In this work, we evaluate the newest generative models (ChatGPT, mT0, and BLOOMZ) in the context of Indic languages. Specifically, we consider natural language generation (NLG) applications such as summarization and questionanswering in monolingual and cross-lingual settings. We observe that current generative models have limited capability for generating text in Indic languages in a zero-shot setting. In contrast, generative models perform consistently better on manual quality-based evaluation in Indic languages and English language generation. Considering limited generation performance, we argue that these LLMs are not intended to use in zero-shot fashion in downstream applications.