Search Results for author:
Found 14 papers, 3 papers with code
RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation
As each representation's cardinality has different trade-offs between performance and computation overhead, extracting highly representative features efficiently and dynamically is both challenging and crucial for SGG.
RECLIP: Resource-efficient CLIP by Training with Small Images
We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining).
MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
As compared to outdoor environments, estimating depth of monocular videos for indoor environments, using self-supervised methods, results in two additional challenges: (i) the depth range of indoor video sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues for training; (ii) the indoor sequences recorded with handheld devices often contain much more rotational motions, which cause difficulties for the pose network to predict accurate relative camera poses.
Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity.
Ranked #30 on
Pose Estimation
on COCO test-dev
Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation
Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks.
Ada-VSR: Adaptive Video Super-Resolution with Meta-Learning
Specifically, meta-learning is employed to obtain adaptive parameters, using a large-scale external dataset, that can adapt quickly to the novel condition (degradation model) of the given test video during the internal learning task, thereby exploiting external and internal information of a video for super-resolution.
Learning Local Recurrent Models for Human Mesh Recovery
We conduct a variety of experiments on standard video mesh recovery benchmark datasets such as Human3. 6M, MPI-INF-3DHP, and 3DPW, demonstrating the efficacy of our design of modeling local dynamics as well as establishing state-of-the-art results based on standard evaluation metrics.
Ranked #44 on
3D Human Pose Estimation
on 3DPW
MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
The effectiveness of each module is shown through a carefully conducted ablation study and the demonstration of the state-of-the-art performance on three indoor datasets, \ie, EuRoC, NYUv2, and 7-scenes.
Fully Convolutional Scene Graph Generation
This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously.
Dynamically Throttleable Neural Networks (TNN)
Conditional computation for Deep Neural Networks (DNNs) reduce overall computational load and improve model accuracy by running a subset of the network.
SAGE: Sequential Attribute Generator for Analyzing Glioblastomas using Limited Dataset
While deep learning approaches have shown remarkable performance in many imaging tasks, most of these methods rely on availability of large quantities of data.
Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations
Various mutations have been shown to correlate with prognosis of High-Grade Glioma (Glioblastoma).
Towards Visually Explaining Variational Autoencoders
We present methods to generate visual attention from the learned latent space, and also demonstrate such attention explanations serve more than just explaining VAE predictions.
An Online Learned Elementary Grouping Model for Multi-target Tracking
We introduce an online approach to learn possible elementary groups (groups that contain only two targets) for inferring high level context that can be used to improve multi-target tracking in a data-association based framework.
