Search Results for author:
Found 43 papers, 22 papers with code
SeisFusion: Constrained Diffusion Model with Input Guidance for 3D Seismic Data Interpolation and Reconstruction
In response to this challenge, we propose a novel diffusion model reconstruction framework tailored for 3D seismic data.
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices.
Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding
Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption.
Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
We propose a model called OTI for ZSVR by employing orthogonal temporal interpolation and the matching loss based on VLMs.
Ranked #1 on
Zero-Shot Action Recognition
on UCF101
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
3rd Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
In our solution, we regard the video panoptic segmentation task as a segmentation target querying task, represent both semantic and instance targets as a set of queries, and then combine these queries with video features extracted by neural networks to predict segmentation masks.
Towards Accurate Post-Training Quantization for Vision Transformer
We find the main reasons lie in (1) the existing calibration metric is inaccurate in measuring the quantization influence for extremely low-bit representation, and (2) the existing quantization paradigm is unfriendly to the power-law distribution of Softmax.
Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention
In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention.
3D Colored Shape Reconstruction from a Single RGB Image through Diffusion
In shape prediction module, the reference RGB image is first encoded into a high-level shape feature and then the shape feature is utilized as a condition to predict the reverse geometric noise in diffusion model.
Bridging Search Region Interaction With Template for RGB-T Tracking
To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module which exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts.
Ranked #2 on
Rgb-T Tracking
on RGBT210
Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond
In this paper, we introduce a novel Generative Adversarial Networks alike framework, referred to as GAN-MAE, where a generator is used to generate the masked patches according to the remaining visible patches, and a discriminator is employed to predict whether the patch is synthesized by the generator.
Multiple Object Tracking Challenge Technical Report for Team MT_IoT
This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments.
Ranked #8 on
Multi-Object Tracking
on DanceTrack
(using extra training data)
Uncertainty-Aware Image Captioning
It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it.
Learning Point-Language Hierarchical Alignment for 3D Visual Grounding
This paper presents a novel hierarchical alignment model (HAM) that learns multi-granularity visual and linguistic representations in an end-to-end manner.
SegViT: Semantic Segmentation with Plain Vision Transformers
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit.
Ranked #4 on
Semantic Segmentation
on COCO-Stuff test
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Meta-Ensemble Parameter Learning
Knowledge distillation is an approach that allows a single model to efficiently capture the approximate performance of an ensemble while showing poor scalability as demand for re-training when introducing new teacher models.
Weakly Supervised Semantic Segmentation via Progressive Patch Learning
"Progressive Patch Learning" further extends the feature destruction and patch learning to multi-level granularities in a progressive manner.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation
To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages.
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios.
Ranked #14 on
Object Detection
on COCO-O
PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding
To alleviate these drawbacks, we propose a one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination.
Efficient Modeling of Future Context for Image Captioning
Existing approaches to image captioning usually generate the sentence word-by-word from left to right, with the constraint of conditioned on local context including the given image and history generated words.
MT-Net Submission to the Waymo 3D Detection Leaderboard
In this technical report, we introduce our submission to the Waymo 3D Detection leaderboard.
Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
In this work, we tackle this challenging issue with a novel range view projection mechanism, and for the first time demonstrate the benefits of fusing multi-frame point clouds for a range-view based detector.
Learn to Cluster Faces via Pairwise Classification
However, they usually suffer from excessive memory consumption especially on large-scale graphs, and rely on empirical thresholds to determine the connectivities between samples in inference, which restricts their applications in various real-world scenes.
PromptDet: Towards Open-vocabulary Detection using Uncurated Images
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations.
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning
On the other hand, InsCon introduces the pull and push of cell-instance, which utilizes cell consistency to enhance fine-grained feature representation for precise boundary localization.
Contrastive Attention Network with Dense Field Estimation for Face Completion
This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images.
Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
Referring Image Segmentation (RIS) aims at segmenting the target object from an image referred by one given natural language expression.
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation
In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation.
Structure Guided Lane Detection
Next, multi-level structural constraints are used to improve the perception of lanes.
Ranked #29 on
Lane Detection
on CULane
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on
Semantic Segmentation
on ADE20K val
Rethinking BiSeNet For Real-time Semantic Segmentation
BiSeNet has been proved to be a popular two-stream network for real-time segmentation.
Ranked #8 on
Real-Time Semantic Segmentation
on Cityscapes test
Large Scale Visual Food Recognition
Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e. g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks.
Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough
Limited by the definition of AP, such methods consider both negative and positive instances ranking before each positive instance.
Ranked #3 on
Vehicle Re-Identification
on VehicleID Large
Scene Text Detection with Scribble Lines
It is a general labeling method for texts with various shapes and requires low labeling costs.
Free-Form Image Inpainting via Contrastive Attention Network
It is difficult for encoders to capture such powerful representations under this complex situation.
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
We call this approach DARTS-.
Ranked #20 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Query Twice: Dual Mixture Attention Meta Learning for Video Summarization
Video summarization aims to select representative frames to retain high-level information, which is usually solved by predicting the segment-wise importance score via a softmax function.
ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network
To encourage further progress in food recognition, we introduce the dataset ISIA Food- 500 with 500 categories from the list in the Wikipedia and 399, 726 images, a more comprehensive food dataset that surpasses existing popular benchmark datasets by category coverage and data volume.
FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition
In this paper, we study how to make use of decentralized datasets for training a robust scene text recognizer while keeping them stay on local devices.
ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition
In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReADS) for general scene text recognition.
