Search Results for author:
Found 50 papers, 15 papers with code
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
A practical navigation agent must be capable of handling a wide range of interaction demands, such as following instructions, searching objects, answering questions, tracking people, and more.
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitoring.
A General Theory for Compositional Generalization
Compositional Generalization (CG) embodies the ability to comprehend novel combinations of familiar concepts, representing a significant cognitive leap in human intellectual advancement.
Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis
Significant progress has been made in scene text detection models since the rise of deep learning, but scene text layout analysis, which aims to group detected text instances as paragraphs, has not kept pace.
VisualCritic: Making LMMs Perceive Visual Quality Like Humans
In this paper, we explore this question and provide the answer "Yes!".
RelationVLM: Making Large Vision-Language Models Understand Visual Relations
The development of Large Vision-Language Models (LVLMs) is striving to catch up with the success of Large Language Models (LLMs), yet it faces more challenges to be resolved.
SeD: Semantic-Aware Discriminator for Image Super-Resolution
In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner.
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Vision-and-language navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions.
Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API
In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automation executor.
Adaptive Frequency Filters As Efficient Global Token Mixers
With this insight, we propose Adaptive Frequency Filtering (AFF) token mixer.
When and Why Momentum Accelerates SGD:An Empirical Study
In the comparison of SGDM and SGD with the same effective learning rate and the same batch size, we observe a consistent pattern: when $\eta_{ef}$ is small, SGDM and SGD experience almost the same empirical training losses; when $\eta_{ef}$ surpasses a certain threshold, SGDM begins to perform better than SGD.
Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators
In specific, we present Responsible Task Automation (ResponsibleTA) as a fundamental framework to facilitate responsible collaboration between LLM-based coordinators and executors for task automation with three empowered capabilities: 1) predicting the feasibility of the commands for executors; 2) verifying the completeness of executors; 3) enhancing the security (e. g., the protection of users' privacy).
Mask-Based Modeling for Neural Radiance Fields
Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model.
Unifying Layout Generation with a Decoupled Diffusion Model
Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation.
Versatile Neural Processes for Learning Implicit Neural Representations
In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions.
Template-guided Hierarchical Feature Restoration for Anomaly Detection
Targeting for detecting anomalies of various sizes for complicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which introduces two key techniques, bottleneck compression and template-guided compensation, for anomaly-free feature restoration.
Ranked #17 on
Anomaly Detection
on MVTec LOCO AD
Image Coding for Machines with Omnipotent Feature Learning
Learning a kind of feature that is both general (for AI tasks) and compact (for compression) is pivotal for its success.
Deep Frequency Filtering for Domain Generalization
Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge.
Active Token Mixer
In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate flexible contextual information distributed across different channels from other tokens into the given query token.
Ranked #64 on
Object Detection
on COCO minival
Mask-based Latent Reconstruction for Reinforcement Learning
For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance.
Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression
Neural video codecs have demonstrated great potential in video transmission and storage applications.
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.
Domain Adaptive Person Re-Identification
Knowledge Distillation
+4
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation
Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks.
MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark
This dataset provides a more reliable benchmark of multi-camera, multi-object tracking systems in cluttered and crowded environments.
Ranked #2 on
Object Tracking
on MMPTRACK
Confounder Identification-free Causal Visual Feature Learning
In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.
Versatile Learned Video Compression
We show that the flow prediction module can largely reduce the transmission cost of voxel flows.
Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
Occluded person re-identification (ReID) aims to match person images with occlusion.
Dual Aspect Self-Attention based on Transformer for Remaining Useful Life Prediction
While deep learning has achieved great success in RUL prediction, existing methods have difficulties in processing long sequences and extracting information from the sensor and time step aspects.
ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation
Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain.
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning.
Continuous Control (100k environment steps)
Continuous Control (500k environment steps)
+4
Soft then Hard: Rethinking the Quantization in Neural Image Compression
Quantization is one of the core components in lossy image compression.
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.
Learned Block-based Hybrid Image Compression
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications.
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss.
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i. e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations.
Causal Contextual Prediction for Learned Image Compression
In this paper, we propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space.
Uncertainty-Aware Few-Shot Image Classification
In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization.
Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID.
Multi-scale Grouped Dense Network for VVC Intra Coding
Versatile Video Coding (H. 266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc.
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation.
Region Normalization for Image Inpainting
In this work, we show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation.
On the Strong Equivalences of LPMLN Programs
Firstly, we present the notions of p-strong and w-strong equivalences between LPMLN programs.
On the Strong Equivalences for LPMLN Programs
In this paper, we study the strong equivalence for LPMLN programs, which is an important tool for program rewriting and theoretical investigations in the field of logic programming.
Logic in Computer Science D.1.6
A Coarse-to-Fine Framework for Learned Color Enhancement with Non-Local Attention
For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously.
CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
We achieve this by the context interaction among the features of different scales.
Relation-Aware Global Attention for Person Re-identification
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i. e., discriminative feature learning.
Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments
Not limited to the control tasks in computationally complex environments, AE-DDPG also achieves higher rewards and 2- to 4-fold improvement in sample efficiency on average compared to other variants of DDPG in MuJoCo environments.
Densely Semantically Aligned Person Re-Identification
We propose a densely semantically aligned person re-identification framework.
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course.
ESmodels: An Epistemic Specification Solver
(To appear in Theory and Practice of Logic Programming (TPLP)) ESmodels is designed and implemented as an experiment platform to investigate the semantics, language, related reasoning algorithms, and possible applications of epistemic specifications. We first give the epistemic specification language of ESmodels and its semantics.
