Search Results for author:
Found 19 papers, 14 papers with code
In-the-Wild Video Question Answering
Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the “in the wild” settings, where the videos are recorded outdoors.
CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models
Recent years have witnessed a significant increase in the performance of Vision and Language tasks.
Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
We create and make publicly available the ACE (Action Co-occurrencE) dataset, consisting of a large graph of ~12k co-occurring pairs of visual actions and their corresponding video clips.
Scalable Performance Analysis for Vision-Language Models
Joint vision-language models have shown great performance over a diverse set of tasks.
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
Not surprisingly, this has, in turn, made many NLP researchers -- especially those at the beginning of their careers -- worry about what NLP research area they should focus on.
Phenaki: Variable Length Video Generation From Open Domain Textual Description
To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.
Ranked #4 on
Video Prediction
on BAIR Robot Pushing
WildQA: In-the-Wild Video Question Answering
Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the "in the wild" settings, where the videos are recorded outdoors.
Ranked #1 on
Video Question Answering
on WildQA
FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval.
When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
We consider the task of temporal human action localization in lifestyle vlogs.
WhyAct: Identifying Action Reasons in Lifestyle Vlogs
We aim to automatically identify human action reasons in online videos.
FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
We propose fill-in-the-blanks as a video understanding evaluation framework and introduce FIBER -- a novel dataset consisting of 28, 000 videos and descriptions in support of this evaluation framework.
LifeQA: A Real-life Dataset for Video Question Answering
We introduce LifeQA, a benchmark dataset for video question answering that focuses on day-to-day real-life situations.
HAHA 2019 Dataset: A Corpus for Humor Analysis in Spanish
This paper presents the development of a corpus of 30, 000 Spanish tweets that were crowd-annotated with humor value and funniness score.
Towards Multimodal Sarcasm Detection (An \_Obviously\_ Perfect Paper)
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
A High Coverage Method for Automatic False Friends Detection for Spanish and Portuguese
In this work we propose a high coverage method that uses word vector representations to build a false friends classifier for any pair of languages, which we apply to the particular case of Spanish and Portuguese.
RETUYT in TASS 2017: Sentiment Analysis for Spanish Tweets using SVM and CNN
This article presents classifiers based on SVM and Convolutional Neural Networks (CNN) for the TASS 2017 challenge on tweets sentiment analysis.
A Crowd-Annotated Spanish Corpus for Humor Analysis
Computational Humor involves several tasks, such as humor recognition, humor generation, and humor scoring, for which it is useful to have human-curated data.
Is This a Joke? Detecting Humor in Spanish Tweets
While humor has been historically studied from a psychological, cognitive and linguistic standpoint, its study from a computational perspective is an area yet to be explored in Computational Linguistics.
