Search Results for author:
Found 39 papers, 27 papers with code
TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
Our method enhances the transmission of LR information in the early stages of diffusion to guarantee image fidelity and stimulates the generation ability of the SD model itself more in the later stages to enhance the detail of generated images.
RFSR: Improving ISR Diffusion Models via Reward Feedback Learning
We posit that introducing reward feedback learning to finetune the existing models can further improve the quality of the generated images.
HyperSeg: Towards Universal Visual Segmentation with Large Language Model
This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs).
Ranked #1 on
Referring Expression Segmentation
on RefCOCO+ val
(using extra training data)
Large Language Model
Open Vocabulary Semantic Segmentation
+8
360-Degree Video Super Resolution and Quality Enhancement Challenge: Methods and Results
In this paper, we outline the challenge framework, detailing the two competition tracks and highlighting the SR solutions proposed by the top-performing models.
Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation
In addition, we introduce a novel task called Referring Multi-Object Tracking and Segmentation (RMOTS) and construct a new dataset named Ref-KITTI Segmentation.
Multi-Object Tracking and Segmentation
Referring Multi-Object Tracking
+3
MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference
For text reference, we align the text feature of stable diffusion priors with the style feature of our IRStyle to perform text-guided color style transfer (TRStyle).
MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis
Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis.
Matten: Video Generation with Mamba-Attention
In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation.
LaSagnA: Language-based Segmentation Assistant for Complex Queries
Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks.
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection
Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos.
Ranked #2 on
Natural Language Moment Retrieval
on ActivityNet Captions
(R@5,IoU=0.5 metric)
InstaGen: Enhancing Object Detection by Training on Synthetic Dataset
The grounding head is trained to align the text embedding of category names with the regional visual feature of the diffusion model, using supervision from an off-the-shelf object detector, and a novel self-training scheme on (novel) categories not covered by the detector.
Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models
Generative models have recently exhibited exceptional capabilities in text-to-image generation but still struggle to generate image sequences coherently.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Temporal Action Localization with Enhanced Instant Discriminability
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video.
Ranked #1 on
Temporal Action Localization
on MultiTHUMOS
MotionTrack: Learning Motion Predictor for Multiple Object Tracking
This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT.
Ranked #9 on
Multi-Object Tracking
on SportsMOT
Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently.
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods.
Ranked #1 on
Video Object Tracking
on SoccerNet-v2
Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network
Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment classification using a pretrained visual-language model.
Ranked #12 on
Zero-Shot Semantic Segmentation
on PASCAL VOC
Adaptive Sparse Pairwise Loss for Object Re-Identification
To address this problem, we propose a novel loss paradigm termed Sparse Pairwise (SP) loss that only leverages few appropriate pairs for each class in a mini-batch, and empirically demonstrate that it is sufficient for the ReID tasks.
TriDet: Temporal Action Detection with Relative Boundary Modeling
In this paper, we present a one-stage framework TriDet for temporal action detection.
Ranked #2 on
Temporal Action Localization
on EPIC-KITCHENS-100
DiP: Learning Discriminative Implicit Parts for Person Re-Identification
In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features.
Ranked #2 on
Person Re-Identification
on CUHK03 detected
AeDet: Azimuth-invariant Multi-view 3D Object Detection
However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization.
Contrastive Video-Language Learning with Fine-grained Frame Sampling
However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
CounTR: Transformer-based Generalised Visual Counting
In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i. e. zero-shot or few-shot counting.
Ranked #3 on
Exemplar-Free Counting
on FSC147
ReAct: Temporal Action Detection with Relational Queries
Moreover, we propose two losses to facilitate and stabilize the training of action classification.
Ranked #17 on
Temporal Action Localization
on THUMOS’14
Cross-Architecture Self-supervised Video Representation Learning
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning.
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
Our DearKD is a two-stage framework that first distills the inductive biases from the early intermediate layers of a CNN and then gives the transformer full play by training without distillation.
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.
InsCLR: Improving Instance Retrieval with Self-Supervision
This work aims at improving instance retrieval with self-supervision.
OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification
Transformers have shown preferable performance on many vision tasks.
Exploring Classification Equilibrium in Long-Tailed Object Detection
Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes.
Ranked #12 on
Object Detection
on LVIS v1.0 val
TOOD: Task-aligned One-stage Object Detection
One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks.
Ranked #3 on
2D Object Detection
on CeyMo
Mutually-aware Sub-Graphs Differentiable Architecture Search
In this paper, we propose a conceptually simple yet efficient method to bridge these two paradigms, referred as Mutually-aware Sub-Graphs Differentiable Architecture Search (MSG-DAS).
Unchain the Search Space with Hierarchical Differentiable Architecture Search
To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level.
Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision
In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations.
Representation Sharing for Fast Object Detector Search and Beyond
FAD consists of a designed search space and an efficient architecture search algorithm.
Compact Deep Aggregation for Set Retrieval
The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors.
GhostVLAD for set-based face recognition
The objective of this paper is to learn a compact representation of image sets for template-based face recognition.
Ranked #3 on
Face Verification
on IJB-A
