no code implementations • 8 May 2024 • Chirag Parikh, Ravi Shankar Mishra, Rohan Chandra, Ravi Kiran Sarvadevabhatla
Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation.
1 code implementation • 12 Apr 2024 • Chirag Parikh, Rohit Saluja, C. V. Jawahar, Ravi Kiran Sarvadevabhatla
Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation.
1 code implementation • 30 Dec 2022 • Prafful Kumar Khoba, Chirag Parikh, Rohit Saluja, Ravi Kiran Sarvadevabhatla, C. V. Jawahar
Along with providing baseline results for existing object detectors on FGVD Dataset, we also present the results of a combination of an existing detector and the recent Hierarchical Residual Network (HRN) classifier for the FGVD task.
no code implementations • 28 Nov 2022 • Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla
We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces.
no code implementations • 10 Nov 2022 • Nikhil Bansal, Kartik Gupta, Kiruthika Kannan, Sivani Pentapati, Ravi Kiran Sarvadevabhatla
Pictionary, the popular sketch-based guessing game, provides an opportunity to analyze shared goal cooperative game play in restricted communication settings.
no code implementations • 27 Sep 2022 • Kushagra Srivastava, Dhruv Patel, Aditya Kumar Jha, Mohhit Kumar Jha, Jaskirat Singh, Ravi Kiran Sarvadevabhatla, Pradeep Kumar Ramancharla, Harikumar Kandath, K. Madhava Krishna
Unmanned Aerial Vehicle (UAV) based remote sensing system incorporated with computer vision has demonstrated potential for assisting building construction and in disaster management like damage assessment during earthquakes.
1 code implementation • 11 Aug 2022 • Neel Trivedi, Ravi Kiran Sarvadevabhatla
At the representation level, we propose a global frame based part stream approach as opposed to conventional modality based streams.
Ranked #13 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • 18 Apr 2022 • Aman Goyal, Dev Agarwal, Anbumani Subramanian, C. V. Jawahar, Ravi Kiran Sarvadevabhatla, Rohit Saluja
In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles.
no code implementations • 10 Apr 2022 • Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla
This skew affects all stages within the pipelines of deep crowd counting approaches.
1 code implementation • 17 Jan 2022 • Arpit Bahety, Rohit Saluja, Ravi Kiran Sarvadevabhatla, Anbumani Subramanian, C. V. Jawahar
We obtain TCDCA of 96. 77% on the test videos, with a remarkable improvement of 22. 58% over baseline, and demonstrate that our counting module's performance is close to human level.
1 code implementation • 21 Oct 2021 • Shubh Maheshwari, Debtanu Gupta, Ravi Kiran Sarvadevabhatla
We introduce MUGL, a novel deep neural model for large-scale, diverse generation of single and multi-person pose-based action sequences with locomotion.
1 code implementation • 17 Oct 2021 • Rishabh Baghel, Abhishek Trivedi, Tejas Ravichandran, Ravi Kiran Sarvadevabhatla
We introduce MeronymNet, a novel hierarchical approach for controllable, part-based generation of multi-category objects using a single unified model.
1 code implementation • 6 Sep 2021 • Samhita Kanaparthy, Manisha Padala, Sankarshan Damle, Ravi Kiran Sarvadevabhatla, Sujit Gujar
F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption.
1 code implementation • 21 Aug 2021 • Prema Satish Sharan, Sowmya Aitha, Amandeep Kumar, Abhishek Trivedi, Aaron Augustine, Ravi Kiran Sarvadevabhatla
Handwritten documents are often characterized by dense and uneven layout.
1 code implementation • 21 Aug 2021 • Abhishek Trivedi, Ravi Kiran Sarvadevabhatla
Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics.
1 code implementation • 19 Aug 2021 • Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla
We analyze the performance of representative crowd counting approaches across standard datasets at per strata level and in aggregate.
1 code implementation • 27 Jun 2021 • Anurag Bagchi, Jazib Mahmood, Dolton Fernandes, Ravi Kiran Sarvadevabhatla
State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited.
Ranked #1 on Temporal Action Localization on THUMOS'14
1 code implementation • 16 Mar 2021 • Meher Shashwat Nigam, Avinash Prabhu, Anurag Sahu, Puru Gupta, Tanvi Karandikar, N. Sai Shankar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna
Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction.
1 code implementation • 27 Jan 2021 • Neel Trivedi, Anirudh Thatipelli, Ravi Kiran Sarvadevabhatla
The lack of fine-grained joints (facial joints, hand fingers) is a fundamental performance bottleneck for state of the art skeleton action recognition models.
Ranked #1 on Skeleton Based Action Recognition on NTU60-X
1 code implementation • 27 Jan 2021 • Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla
We deploy SynSE for the task of skeleton-based action sequence recognition.
no code implementations • 3 Oct 2020 • Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna
In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learned features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence, and pose graph submodules of the SLAM pipeline.
1 code implementation • 4 Jul 2020 • Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal, Shubh Maheshwari, Neel Trivedi, Sourav Das, Ravi Kiran Sarvadevabhatla
To study skeleton-action recognition in the wild, we introduce Skeletics-152, a curated and 3-D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset.
Ranked #1 on Skeleton Based Action Recognition on Skeletics-152
no code implementations • 30 May 2020 • Rishabh Baghel, Ravi Kiran Sarvadevabhatla
We propose OPAL-Net, a novel hierarchical architecture for part-based layout generation of objects from multiple categories using a single unified model.
1 code implementation • 16 Feb 2020 • Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna
At the intermediate level, the map is represented as a Manhattan Graph where the nodes and edges are characterized by Manhattan properties and as a Pose Graph at the lower-most level of detail.
1 code implementation • 15 Dec 2019 • Abhishek Prusty, Sowmya Aitha, Abhishek Trivedi, Ravi Kiran Sarvadevabhatla
To address this deficiency, we introduce Indiscapes, the first ever dataset with multi-regional layout annotations for historical Indic manuscripts.
Instance Segmentation Optical Character Recognition (OCR) +1
no code implementations • 19 Jul 2018 • K L Navaneet, Ravi Kiran Sarvadevabhatla, Shashank Shekhar, R. Venkatesh Babu, Anirban Chakraborty
Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras.
1 code implementation • 29 Jan 2018 • Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal, Venkatesh Babu Radhakrishnan
Similarly, performance on multi-disciplinary tasks such as Visual Question Answering (VQA) is considered a marker for gauging progress in Computer Vision.
1 code implementation • 5 Sep 2017 • Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas, Sahil Manocha, R. Venkatesh Babu
We propose SketchParse, the first deep-network architecture for fully automatic parsing of freehand object sketches.
2 code implementations • CVPR 2017 • Swaminathan Gurumurthy, Ravi Kiran Sarvadevabhatla, Venkatesh Babu Radhakrishnan
A class of recent approaches for generating images, called Generative Adversarial Networks (GAN), have been used to generate impressively realistic images of objects, bedrooms, handwritten digits and a variety of other image modalities.
no code implementations • 20 Mar 2017 • Ravi Kiran Sarvadevabhatla, Sudharshan Suresh, R. Venkatesh Babu
In this paper, we analyze the results of a free-viewing gaze fixation study conducted on 3904 freehand sketches distributed across 160 object categories.
no code implementations • 23 Nov 2016 • Ravi Kiran Sarvadevabhatla, Shanthakumar Venkatraman, R. Venkatesh Babu
Our results show that the proposed benchmarking procedure enables additional differentiation among state-of-the-art object classifiers in terms of their ability to handle missing content and insufficient object detail.
1 code implementation • 11 Aug 2016 • Ravi Kiran Sarvadevabhatla, Jogendra Kundu, Babu R. Venkatesh
In our work, we propose a recurrent neural network architecture for sketch object recognition which exploits the long-term sequential and structural regularities in stroke data in a scalable manner.
1 code implementation • 29 Jul 2016 • Ravi Kiran Sarvadevabhatla, Shiv Surya, Srinivas S. S. Kruthiventi, Venkatesh Babu R
Current state of the art object recognition architectures achieve impressive performance but are typically specialized for a single depictive style (e. g. photos only, sketches only).
no code implementations • 25 Jan 2016 • Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S. S. Kruthiventi, R. Venkatesh Babu
With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective.
no code implementations • 15 Sep 2015 • Ravi Kiran Sarvadevabhatla, Venkatesh Babu R
Studies from neuroscience show that part-mapping computations are employed by human visual system in the process of object recognition.
1 code implementation • 25 May 2015 • Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu
With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python.
no code implementations • 1 Feb 2015 • Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu
Therefore, analyzing such sparse sketches can aid our understanding of the neuro-cognitive processes involved in visual representation and recognition.
no code implementations • 31 Jan 2015 • Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu
Freehand line sketches are an interesting and unique form of visual representation.