Search Results for author:
Found 25 papers, 11 papers with code
Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution
To address these issues, we propose a novel multimodal self-evolution framework that enables the model to autonomously generate high-quality questions and answers using only unannotated images.
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
MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model
Tracking by detection has been the prevailing paradigm in the field of Multi-object Tracking (MOT).
Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models
To address this limitation, we explore the potential of diffusion models that simultaneously consider all input humans and the floor plan to generate plausible 3D scenes.
PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions
We evaluated 60 representative models, including top-down, bottom-up, heatmap-based, regression-based, and classification-based methods, across three datasets for human and animal pose estimation.
Towards Variable and Coordinated Holistic Co-Speech Motion Generation
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination.
Contact-aware Human Motion Generation from Textual Descriptions
This paper addresses the problem of generating 3D interactive human motion from text.
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
GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction
Demystifying complex human-ground interactions is essential for accurate and realistic 3D human motion reconstruction from RGB videos, as it ensures consistency between the humans and the ground plane.
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 #10 on
Multi-Object Tracking
on SportsMOT
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
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
Generating Holistic 3D Human Motion from Speech
This work addresses the problem of generating 3D holistic body motions from human speech.
Ranked #3 on
3D Face Animation
on BEAT2
Learning Sequence Representations by Non-local Recurrent Neural Memory
The key challenge of sequence representation learning is to capture the long-range temporal dependencies.
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
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.
MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames
In this paper, we consider a novel problem of reconstructing a 3D human avatar from multiple unconstrained frames, independent of assumptions on camera calibration, capture space, and constrained actions.
View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
Different frequency bands in the trajectory spectrums could hierarchically reflect agents' motion preferences at different scales.
Ranked #2 on
Trajectory Prediction
on ETH/UCY
FEATURE-AUGMENTED HYPERGRAPH NEURAL NETWORKS
In FAHGNN, we explore the influence of node features for the expressive power of GNNs and augment features by introducing common features and personal features to model information.
OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification
Transformers have shown preferable performance on many vision tasks.
Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
Person re-identification aims to identify whether pairs of images belong to the same person or not.
Non-local Recurrent Neural Memory for Supervised Sequence Modeling
Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies.
VGGFace2: A dataset for recognising faces across pose and age
The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Template Adaptation for Face Verification and Identification
Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset for imagery and the YouTubeFaces dataset for videos.
Ranked #9 on
Face Verification
on IJB-A
