Search Results for author:
Found 33 papers, 6 papers with code
Shuffle and Attend: Video Domain Adaptation
As the first novelty, we propose an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level (cf.
Ranked #3 on
Unsupervised Domain Adaptation
on UCF-HMDB
OmniVec: Learning robust representations with cross modal sharing
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.
Ranked #1 on
Image Classification
on ImageNet
Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction
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.
Texture Representation via Analysis and Synthesis with Generative Adversarial Networks
We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks.
K-12BERT: BERT for K-12 education
However, there has not been a model specifically adapted for the education domain (particularly K-12) across subjects to the best of our knowledge.
Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2
We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework.
Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention
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.
Depth Infused Binaural Audio Generation using Hierarchical Cross-Modal Attention
Binaural audio gives the listener the feeling of being in the recording place and enhances the immersive experience if coupled with AR/VR.
Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs
On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously.
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks
As a second contribution, we propose to improve the graph construction for GNNs for 3D point clouds.
Ranked #1 on
3D Part Segmentation
on ShapeNet-Part
Discriminative Semantic Transitive Consistency for Cross-Modal Learning
Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space.
Beyond Image to Depth: Improving Depth Prediction using Echoes
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.
Object Detection with a Unified Label Space from Multiple Datasets
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.
Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos
We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos.
Ranked #5 on
GZSL Video Classification
on VGGSound-GZSL(main)
Video Person Re-Identification using Learned Clip Similarity Aggregation
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.
Optical Flow Estimation
Video-Based Person Re-Identification
A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography
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.
Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehicles
We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios.
3D Object Detection
3D Object Detection From Monocular Images
+4
Zero-Shot Object Detection
We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training.
Unsupervised Learning of Face Representations
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.
A Generative Model for Dynamic Networks with Applications
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.
Vehicle Tracking in Wide Area Motion Imagery via Stochastic Progressive Association Across Multiple Frames (SPAAM)
The stochastic dis-association at each iteration maintains each estimated association according to an estimated probability for confidence, obtained via a probabilistic model.
An Empirical Evaluation of Visual Question Answering for Novel Objects
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.
Large Scale Novel Object Discovery in 3D
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.
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos
We propose a novel method for temporally pooling frames in a video for the task of human action recognition.
Deep fusion of visual signatures for client-server facial analysis
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.
Discriminatively Trained Latent Ordinal Model for Video Classification
We study the problem of video classification for facial analysis and human action recognition.
CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval
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.
LOMo: Latent Ordinal Model for Facial Analysis in Videos
We study the problem of facial analysis in videos.
Latent Embeddings for Zero-shot Classification
We train the model with a ranking based objective function which penalizes incorrect rankings of the true class for a given image.
Local Higher-Order Statistics (LHS) describing images with statistics of local non-binarized pixel patterns
We propose a new image representation for texture categorization and facial analysis, relying on the use of higher-order local differential statistics as features.
Scalable Nonlinear Embeddings for Semantic Category-based Image Retrieval
We propose a novel algorithm for the task of supervised discriminative distance learning by nonlinearly embedding vectors into a low dimensional Euclidean space.
Expanded Parts Model for Semantic Description of Humans in Still Images
We validate our method on three recent challenging datasets of human attributes and actions.
Expanded Parts Model for Human Attribute and Action Recognition in Still Images
We propose a new model for recognizing human attributes (e. g. wearing a suit, sitting, short hair) and actions (e. g. running, riding a horse) in still images.
