Search Results for author:
Found 17 papers, 8 papers with code
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge.
Self-Sufficient Framework for Continuous Sign Language Recognition
The goal of this work is to develop self-sufficient framework for Continuous Sign Language Recognition (CSLR) that addresses key issues of sign language recognition.
Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models.
Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition
Most existing Continuous Sign Language Recognition (CSLR) benchmarks have fixed backgrounds and are filmed in studios with a static monochromatic background.
Generative Bias for Robust Visual Question Answering
In this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias model directly from the target model, called GenB.
Single-Modal Entropy based Active Learning for Visual Question Answering
In this work, we address Active Learning in the multi-modal setting of Visual Question Answering (VQA).
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.
Ranked #42 on
Human-Object Interaction Detection
on HICO-DET
LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
In order to find the uncertain points, we generate an inconsistency mask using the proposed adaptive pixel selector and we label these segment-based regions to achieve near supervised performance with only a small fraction (about 2. 2%) ground truth points, which we call "Segment based Pixel-Labeling (SPL)".
MCDAL: Maximum Classifier Discrepancy for Active Learning
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters.
DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data.
Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation
In this work, we address the issues of missing modalities that have arisen from the Visual Question Answer-Difference prediction task and find a novel method to solve the task at hand.
OGLE-2017-BLG-1049: Another giant planet microlensing event
From this, we find that the lens system has a star with mass $M_{\rm h}=0. 55^{+0. 36}_{-0. 29} \ M_{\odot}$ hosting a giant planet with $M_{\rm p}=5. 53^{+3. 62}_{-2. 87} \ M_{\rm Jup}$, at a distance of $D_{\rm L}=5. 67^{+1. 11}_{-1. 52}\ {\rm kpc}$.
Earth and Planetary Astrophysics Astrophysics of Galaxies
Dense Relational Image Captioning via Multi-task Triple-Stream Networks
To this end, we propose the multi-task triple-stream network (MTTSNet) which consists of three recurrent units responsible for each POS which is trained by jointly predicting the correct captions and POS for each word.
Detecting Human-Object Interactions with Action Co-occurrence Priors
A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution.
Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption.
Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
Our goal in this work is to train an image captioning model that generates more dense and informative captions.
Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
Human behavior understanding is arguably one of the most important mid-level components in artificial intelligence.
