Search Results for author:
Found 38 papers, 13 papers with code
Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information
Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation.
Dual-Level Decoupled Transformer for Video Captioning
As for the latter, \textbf{\textit{"couple"}} means treating the generation of visual semantic and syntax-related words equally.
Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs
Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions.
CapOnImage: Context-driven Dense-Captioning on Image
Existing image captioning systems are dedicated to generating narrative captions for images, which are spatially detached from the image in presentation.
Self-Supervised Text Erasing with Controllable Image Synthesis
The synthetic training images with erasure ground-truth are then fed to train a coarse-to-fine erasing network.
Estimation of Reliable Proposal Quality for Temporal Action Detection
For the region perspective, we introduce Region Evaluate Module (REM) which uses a new and efficient sampling method for proposal feature representation containing more contextual information compared with point feature to refine category score and proposal boundary.
Structure-Aware Motion Transfer with Deformable Anchor Model
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
Learning Pixel-Level Distinctions for Video Highlight Detection
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
Rapid Scalable Distributed Power Flow with Open-Source Implementation
This new variant is characterized by using a reduced modelling method of the distributed AC PF problem, which is reformulated as a zero-residual least-squares problem with consensus constraints.
Over-the-Air Federated Learning via Second-Order Optimization
To address this issue, in this paper, we instead propose a novel over-the-air second-order federated optimization algorithm to simultaneously reduce the communication rounds and enable low-latency global model aggregation.
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning
Under the non-convex setting, we derive the convergence performance of the FedZO algorithm and characterize the impact of the numbers of local iterates and participating edge devices on the convergence.
Move As You Like: Image Animation in E-Commerce Scenario
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
Robust Resource-Aware Self-triggered Model Predictive Control
The wide adoption of wireless devices in the Internet of Things requires controllers that are able to operate with limited resources, such as battery life.
Boosting Image Outpainting with Semantic Layout Prediction
Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.
We Know What You Want: An Advertising Strategy Recommender System for Online Advertising
To achieve this goal, the advertising platform needs to identify the advertiser's optimization objectives, and then recommend the corresponding strategies to fulfill the objectives.
Over-the-Air Computation via Reconfigurable Intelligent Surface
Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property of multiple-access channels.
Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approach
Let a labeled dataset be given with scattered samples and consider the hypothesis of the ground-truth belonging to the reproducing kernel Hilbert space (RKHS) of a known positive-definite kernel.
Learning the Best Pooling Strategy for Visual Semantic Embedding
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions.
Distributed Optimization for Massive Connectivity
Massive device connectivity in Internet of Thing (IoT) networks with sporadic traffic poses significant communication challenges.
ALADIN-$α$ -- An open-source MATLAB toolbox for distributed non-convex optimization
This paper introduces an open-source software for distributed and decentralized non-convex optimization named ALADIN-$\alpha$.
Controllable Person Image Synthesis with Attribute-Decomposed GAN
This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e. g., pose, head, upper clothes and pants) provided in various source inputs.
Ranked #6 on
Pose Transfer
on Deep-Fashion
DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories
We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map.
FoveaBox: Beyound Anchor-based Object Detection
While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors.
SOLO: Segmenting Objects by Locations
We present a new, embarrassingly simple approach to instance segmentation in images.
Ranked #34 on
Instance Segmentation
on COCO test-dev
Task-Aware Monocular Depth Estimation for 3D Object Detection
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
Effective Domain Knowledge Transfer with Soft Fine-tuning
However, the datasets from source domain are simply discarded in the fine-tuning process.
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts.
FoveaBox: Beyond Anchor-based Object Detector
In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate. We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis.
Ranked #93 on
Object Detection
on COCO test-dev
(APM metric)
Consistent Optimization for Single-Shot Object Detection
We present consistent optimization for single stage object detection.
Acquisition of Localization Confidence for Accurate Object Detection
The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.
Ranked #153 on
Object Detection
on COCO test-dev
Unified Perceptual Parsing for Scene Understanding
In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image.
Ranked #67 on
Semantic Segmentation
on ADE20K val
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples
Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of current frameworks and image-text datasets (e. g., MS-COCO) both quantitatively and qualitatively.
Repulsion Loss: Detecting Pedestrians in a Crowd
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
Ranked #7 on
Pedestrian Detection
on Caltech
(using extra training data)
MegDet: A Large Mini-Batch Object Detector
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design.
What Can Help Pedestrian Detection?
Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods.
Ranked #13 on
Pedestrian Detection
on Caltech
FastMask: Segment Multi-scale Object Candidates in One Shot
Objects appear to scale differently in natural images.
UnitBox: An Advanced Object Detection Network
In present object detection systems, the deep convolutional neural networks (CNNs) are utilized to predict bounding boxes of object candidates, and have gained performance advantages over the traditional region proposal methods.
Learning Deep Face Representation
Our basic network is capable of achieving high recognition accuracy ($85. 8\%$ on LFW benchmark) with only 8 dimension representation.
