Search Results for author:
Found 30 papers, 22 papers with code
Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
Our approach achieves the state-of-the-art performances on both temporal action proposal task and temporal action localization task.
Ranked #11 on
Temporal Action Proposal Generation
on ActivityNet-1.3
Single Shot Temporal Action Detection
The main drawback of this framework is that the boundaries of action instance proposals have been fixed during the classification step.
Face Spoofing Detection by Fusing Binocular Depth and Spatial Pyramid Coding Micro-Texture Features
The second one is a high-level micro-texture based feature called Spatial Pyramid Coding Micro-Texture (SPMT) feature.
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content.
Ranked #3 on
Temporal Action Proposal Generation
on THUMOS' 14
Discriminative Representation Combinations for Accurate Face Spoofing Detection
Secondly we utilize the SSD, which is a deep learning framework for detection, to excavate context cues and conduct end-to-end face presentation attack detection.
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
Weakly supervised temporal action localization, which aims at temporally locating action instances in untrimmed videos using only video-level class labels during training, is an important yet challenging problem in video analysis.
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Ranked #1 on
Action Recognition
on THUMOS’14
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance.
Ranked #33 on
Action Recognition
on Something-Something V1
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Learning Semantic Person Image Generation by Region-Adaptive Normalization
In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style.
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.
Paint Transformer: Feed Forward Neural Painting with Stroke Prediction
Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks.
Ranked #1 on
Object Detection
on A2D
Background-Click Supervision for Temporal Action Localization
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion.
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
We propose a novel framework, i. e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of manipulations.
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel.
Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation.
Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion
Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task.
Ranked #10 on
Robust Camera Only 3D Object Detection
on nuScenes-C
AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer
Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair.
Planning-oriented Autonomous Driving
Oriented at this, we revisit the key components within perception and prediction, and prioritize the tasks such that all these tasks contribute to planning.
DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Our key idea is to investigate and identify a space, namely delta image and text space that has well-aligned distribution between CLIP visual feature differences of two images and CLIP textual embedding differences of source and target texts.
Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
On the other hand, different from the vanilla version, we adopt a learnable scaling operation on content features before content-style feature interaction, which better preserves the original similarity between a pair of content features while ensuring the stylization quality.
Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
Firstly, it reduces the computational complexity of temporal fusion from $O(T)$ to $O(1)$, resulting in significant improvements in inference speed and memory usage.
DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection
In this work, we propose a novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single-frame (static branch).
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes.
Ranked #1 on
3D Semantic Scene Completion
on KITTI-360
3D Semantic Scene Completion from a single RGB image
Autonomous Driving
Sparse4D v3: Advancing End-to-End 3D Detection and Tracking
We introduce two auxiliary training tasks (Temporal Instance Denoising and Quality Estimation) and propose decoupled attention to make structural improvements, leading to significant enhancements in detection performance.
Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation
For the first objective, we identify the implicit grounding capability of IP2P from the cross-attention between instruction and image, then develop an effective mask extraction method.
EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction
Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors.
WidthFormer: Toward Efficient Transformer-based BEV View Transformation
In this work, we present WidthFormer, a novel transformer-based Bird's-Eye-View (BEV) 3D detection method tailored for real-time autonomous-driving applications.
HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks.
Ranked #70 on
Visual Question Answering
on MM-Vet
