Search Results for author: Kyle Min

Found 6 papers, 4 papers with code

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection

2 code implementations15 Jul 2022 Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar

Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows.

Audio-Visual Active Speaker Detection Graph Learning +1

Learning Spatial-Temporal Graphs for Active Speaker Detection

no code implementations2 Dec 2021 Sourya Roy, Kyle Min, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar

We address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between audio and visual data.

Audio-Visual Active Speaker Detection Node Classification

Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization

1 code implementation ECCV 2020 Kyle Min, Jason J. Corso

Two triplets of the feature space are considered in our approach: one triplet is used to learn discriminative features for each activity class, and the other one is used to distinguish the features where no activity occurs (i. e. background features) from activity-related features for each video.

Metric Learning Weakly Supervised Action Localization +1

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection

1 code implementation ICCV 2019 Kyle Min, Jason J. Corso

It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the encoded features spatially while aggregating all the temporal information.

Video Saliency Detection

Hierarchical Novelty Detection for Visual Object Recognition

no code implementations CVPR 2018 Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee

The essential ingredients of our methods are confidence-calibrated classifiers, data relabeling, and the leave-one-out strategy for modeling novel classes under the hierarchical taxonomy.

Generalized Zero-Shot Learning Object Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.