Search Results for author:
Found 13 papers, 7 papers with code
Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.
Ranked #3 on
Dense Video Captioning
on YouCook2
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
To this end, we introduce a Self-Training framework for SGG (ST-SGG) that assigns pseudo-labels for unannotated triplets based on which the SGG models are trained.
LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations.
Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network
Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image.
Information Elevation Network for Fast Online Action Detection
Consequently, the forget gate of the original LSTM can lose the accumulated information relevant to the current action because it determines which information to forget without considering the current action.
Learning to Discriminate Information for Online Action Detection: Analysis and Application
To overcome this problem, we propose a novel recurrent unit, named Information Discrimination Unit (IDU), which explicitly discriminates the information relevancy between an ongoing action and others to decide whether to accumulate the input information.
Learning to Combine the Modalities of Language and Video for Temporal Moment Localization
Temporal moment localization aims to retrieve the best video segment matching a moment specified by a query.
Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting
This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020.
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
By using the proposed temporal modeling method (T-OSA), and the efficient factorized component (D(2+1)D), we construct two types of VoV3D networks, VoV3D-M and VoV3D-L.
Ranked #29 on
Action Recognition
on Something-Something V1
(using extra training data)
Learning to Discriminate Information for Online Action Detection
For online action detection, in this paper, we propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others.
Ranked #13 on
Online Action Detection
on TVSeries
SRG: Snippet Relatedness-based Temporal Action Proposal Generator
Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries.
Extensible Hierarchical Method of Detecting Interactive Actions for Video Understanding
In addition, most studies have not considered extensibility for a newly added action that has been previously trained.
Ranked #1 on
Action Recognition
on ActionNet-VE
ActionNet-VE Dataset: A Dataset for Describing Visual Events by Extending VIRAT Ground 2.0
This paper introduces a dataset for recognizing and describing interactive events between objects of interest including persons, cars, bikes, and carried objects.
