Search Results for author:
Found 13 papers, 6 papers with code
Harnessing Temporal Causality for Advanced Temporal Action Detection
As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries.
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing.
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1, 536 frames, leading to significant detection performance.
Ranked #1 on
Temporal Action Localization
on EPIC-KITCHENS-100
A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector
Some existing methods build one-stage pipelines, But a large performance drop exists with the vanilla one-stage pipeline and extra classification modules are needed to achieve comparable performance.
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy.
Salvage of Supervision in Weakly Supervised Object Detection
However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD.
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
In this paper we introduce ApproxDet, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios.
Rethinking the Route Towards Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels.
Ranked #2 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric)
Towards Real-Time Action Recognition on Mobile Devices Using Deep Models
We show that pre-trained weights on ImageNet improve the accuracy under the real-time action recognition setting.
Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
Inspired by the coarse-to-fine hierarchical process, we propose an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification.
Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming
Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications.
Ranked #11 on
Single-object discovery
on COCO_20k
Deep Descriptor Transforming for Image Co-Localization
Reusable model design becomes desirable with the rapid expansion of machine learning applications.
Minimal Gated Unit for Recurrent Neural Networks
Recently recurrent neural networks (RNN) has been very successful in handling sequence data.
