Search Results - "Min, Kyle"

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection by Min, Kyle, Corso, Jason

“…TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network…”
Get full text

Hierarchical Novelty Detection for Visual Object Recognition by Lee, Kibok, Lee, Kimin, Min, Kyle, Zhang, Yuting, Shin, Jinwoo, Lee, Honglak

“…Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing…”
Get full text

SViTT: Temporal Learning of Sparse Video-Text Transformers by Li, Yi, Min, Kyle, Tripathi, Subarna, Vasconcelos, Nuno

“…Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data,…”
Get full text

Integrating Human Gaze into Attention for Egocentric Activity Recognition by Min, Kyle, Corso, Jason J.

“…It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze…”
Get full text

Unbiased Scene Graph Generation in Videos by Nag, Sayak, Min, Kyle, Tripathi, Subarna, Roy-Chowdhury, Amit K.

“…The task of dynamic scene graph generation (SGG) from videos is complicated and challenging due to the inherent dynamics of a scene, temporal fluctuation of…”
Get full text

STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization by Min, Kyle

“…This report introduces our novel method named STHG for the Audio-Visual Diarization task of the Ego4D Challenge 2023. Our key innovation is that we model all…”
Get full text

Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization by Min, Kyle

“…This report describes our approach for the Audio-Visual Diarization (AVD) task of the Ego4D Challenge 2022. Specifically, we present multiple technical…”
Get full text

SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Video by Valdez, Hector A, Min, Kyle, Tripathi, Subarna

“…Pretraining egocentric vision-language models has become essential to improving downstream egocentric video-text tasks. These egocentric foundation models…”
Get full text

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model by Kim, Changhoon, Min, Kyle, Yang, Yezhou

“…In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces…”
Get full text

Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation by Wu, Tz-Ying, Min, Kyle, Tripathi, Subarna, Vasconcelos, Nuno

“…Video understanding typically requires fine-tuning the large backbone when adapting to new domains. In this paper, we leverage the egocentric video foundation…”
Get full text

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models by Kim, Changhoon, Min, Kyle, Patel, Maitreya, Cheng, Sheng, Yang, Yezhou

“…The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual de-scriptions, has concurrently escalated critical…”
Get full text

Contrastive Language Video Time Pre-training by Liu, Hengyue, Min, Kyle, Valdez, Hector A, Tripathi, Subarna

“…We introduce LAVITI, a novel approach to learning language, video, and temporal representations in long-form videos via contrastive learning. Different from…”
Get full text

Integrating Human Gaze into Attention for Egocentric Activity Recognition by Min, Kyle, Corso, Jason J

“…It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze…”
Get full text

Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization by Min, Kyle, Corso, Jason J

“…Temporally localizing activities within untrimmed videos has been extensively studied in recent years. Despite recent advances, existing methods for…”
Get full text

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models by Kim, Changhoon, Min, Kyle, Patel, Maitreya, Cheng, Sheng, Yang, Yezhou

“…The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual descriptions, has concurrently escalated critical…”
Get full text

SViTT: Temporal Learning of Sparse Video-Text Transformers by Li, Yi, Min, Kyle, Tripathi, Subarna, Vasconcelos, Nuno

“…Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data,…”
Get full text

Unbiased Scene Graph Generation in Videos by Nag, Sayak, Min, Kyle, Tripathi, Subarna, Chowdhury, Amit K. Roy

“…The task of dynamic scene graph generation (SGG) from videos is complicated and challenging due to the inherent dynamics of a scene, temporal fluctuation of…”
Get full text

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection by Min, Kyle, Corso, Jason J

“…TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network…”
Get full text

Action Scene Graphs for Long-Form Understanding of Egocentric Videos by Rodin, Ivan, Furnari, Antonino, Min, Kyle, Tripathi, Subarna, Farinella, Giovanni Maria

“…We present Egocentric Action Scene Graphs (EASGs), a new representation for long-form understanding of egocentric videos. EASGs extend standard…”
Get full text

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection by Min, Kyle, Roy, Sourya, Tripathi, Subarna, Guha, Tanaya, Majumdar, Somdeb

“…Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and…”
Get full text