no code implementations • 24 Apr 2024 • Samyak Rawlekar, Shubhang Bhatnagar, Vishnuvardhan Pogunulu Srinivasulu, Narendra Ahuja
Multi-label Recognition (MLR) involves the identification of multiple objects within an image.
no code implementations • 22 Mar 2024 • Shubhang Bhatnagar, Narendra Ahuja
For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point.
no code implementations • 16 Jan 2024 • Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja
Our method simultaneously estimates the visible (explicit) representation (3D shapes, colors, camera parameters) and the implicit skeletal representation, from motion cues in the object video without 3D supervision.
no code implementations • 9 Dec 2023 • Hao Zhang, Fang Li, Lu Qi, Ming-Hsuan Yang, Narendra Ahuja
Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes.
no code implementations • 25 Oct 2023 • Hao Zhang, Fang Li, Narendra Ahuja
Current techniques for NeRF decomposition involve a trade-off between the flexibility of processing open-vocabulary queries and the accuracy of 3D segmentation.
no code implementations • 9 Aug 2023 • Shubhang Bhatnagar, Sharath Gopal, Narendra Ahuja, Liu Ren
We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.
no code implementations • 29 Oct 2022 • Moitreya Chatterjee, Narendra Ahuja, Anoop Cherian
In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio.
1 code implementation • 22 Nov 2021 • Aniket Shirke, Aziz Saifuddin, Achleshwar Luthra, Jiangong Li, Tawni Williams, Xiaodan Hu, Aneesh Kotnana, Okan Kocabalkanli, Narendra Ahuja, Angela Green-Miller, Isabella Condotta, Ryan N. Dilger, Matthew Caesar
We identify the adjacent camera and the shared pig location on the floor at the handover time using inter-view homography.
no code implementations • ICCV 2021 • Moitreya Chatterjee, Narendra Ahuja, Anoop Cherian
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena.
no code implementations • ICCV 2021 • Moitreya Chatterjee, Jonathan Le Roux, Narendra Ahuja, Anoop Cherian
At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention.
1 code implementation • ICCV 2021 • Xiaodan Hu, Narendra Ahuja
Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre).
no code implementations • 1 Jan 2021 • Moitreya Chatterjee, Anoop Cherian, Narendra Ahuja
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena.
no code implementations • ECCV 2020 • Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja
To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of audio and past frames.
no code implementations • ECCV 2018 • Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja
We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters.
1 code implementation • CVPR 2018 • Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, Jia-Bin Huang
We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction.
no code implementations • 11 Oct 2017 • Yijun Li, Jia-Bin Huang, Narendra Ahuja, Ming-Hsuan Yang
In contrast to existing methods that consider only the guidance image, the proposed algorithm can selectively transfer salient structures that are consistent with both guidance and target images.
2 code implementations • 5 Oct 2017 • Shun Zhang, Jia-Bin Huang, Jongwoo Lim, Yihong Gong, Jinjun Wang, Narendra Ahuja, Ming-Hsuan Yang
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up.
7 code implementations • 4 Oct 2017 • Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, Ming-Hsuan Yang
However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results.
1 code implementation • CVPR 2017 • Le Zhang, Jagannadan Varadarajan, Ponnuthurai Nagaratnam Suganthan, Narendra Ahuja, Pierre Moulin
Unlike conventional orthogonal decision trees that use a single feature and heuristic measures to obtain a split at each node, we propose to use a more powerful proximal SVM to obtain oblique hyperplanes to capture the geometric structure of the data better.
1 code implementation • CVPR 2017 • Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, Ming-Hsuan Yang
Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution.
Ranked #40 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • CVPR 2016 • Jia-Bin Huang, Rich Caruana, Andrew Farnsworth, Steve Kelling, Narendra Ahuja
In this paper, we present a vision-based system for detecting migrating birds in flight at night.
no code implementations • CVPR 2016 • Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, Narendra Ahuja, Ming-Hsuan Yang
Using these datasets, we conduct a large-scale user study to quantify the performance of several representative state-of-the-art blind deblurring algorithms.
1 code implementation • 20 May 2016 • Xing Wei, Qingxiong Yang, Yihong Gong, Ming-Hsuan Yang, Narendra Ahuja
Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.
no code implementations • ICCV 2015 • Elisa Ricci, Jagannadan Varadarajan, Ramanathan Subramanian, Samuel Rota Bulo, Narendra Ahuja, Oswald Lanz
We present a novel approach for jointly estimating tar- gets' head, body orientations and conversational groups called F-formations from a distant social scene (e. g., a cocktail party captured by surveillance cameras).
no code implementations • ICCV 2015 • Avinash Kumar, Narendra Ahuja
Using a thick-lens setting, we show that such a back-projection is more accurate than the two-step method of undistorting an image pixel and then back-projecting it.
no code implementations • CVPR 2015 • Jia-Bin Huang, Abhishek Singh, Narendra Ahuja
However, the internal dictionary obtained from the given image may not always be sufficiently expressive to cover the textural appearance variations in the scene.
no code implementations • CVPR 2015 • Tianzhu Zhang, Si Liu, Changsheng Xu, Shuicheng Yan, Bernard Ghanem, Narendra Ahuja, Ming-Hsuan Yang
Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates.
no code implementations • CVPR 2014 • Abhishek Singh, Fatih Porikli, Narendra Ahuja
We then show that by taking a convex combination of orientation and frequency selective bands of the noisy and the denoised HR images, we can obtain a desired HR image where (i) some of the textural signal lost in the denoising step is effectively recovered in the HR domain, and (ii) additional textures can be easily synthesized by appropriately constraining the parameters of the convex combination.
no code implementations • CVPR 2014 • Avinash Kumar, Narendra Ahuja
The second approach based on decentering distortion modeling is approximate as it can only handle small tilts and cannot explicitly estimate the sensor tilt.
no code implementations • CVPR 2014 • Xianbiao Shu, Fatih Porikli, Narendra Ahuja
Low-rank matrix recovery from a corrupted observation has many applications in computer vision.
no code implementations • CVPR 2014 • Tianzhu Zhang, Kui Jia, Changsheng Xu, Yi Ma, Narendra Ahuja
The proposed part matching tracker (PMT) has a number of attractive properties.