Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks68 from public data
- Deep feature learning with relative distance comparison for person re-identification687
A scalable distance driven feature learning framework based on the deep neural network for person re-identification that achieves very promising results and outperforms other state-of-the-art approaches.
- EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning206
A pruning method called EagleEye is presented, in which a simple yet efficient evaluation component based on adaptive batch normalization is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy.
- Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation201
This work proposes to modularize the large search space of NAS into blocks to ensure that the potential candidate architectures are fully trained, and distill the neural architecture (DNA) knowledge from a teacher model to supervise the block-wise architecture search, which significantly improves the effectiveness of NAS.
- Dynamic Slimmable Network195
A dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
- Distance metric optimization driven convolutional neural network for age invariant face recognition192
A novel distance metric optimization driven learning approach that integrates these traditional steps via a deep convolutional neural network, which learns feature representations and the decision function in an end-to-end way, and can be optimized simultaneously by backward propagation.
- 147
- BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search128
This work presents Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of in-accurate architecture rating caused by large weight-sharing space and biased supervision in previous methods
- Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking96
This work examines the insecurity of current best-performing ReID models by proposing a learning-to-mis-rank formulation to perturb the ranking of the system output and performs a back-box attack by developing a novel multi-stage network architecture that pyramids the features of different levels to extract general and transferable features for the adversarial perturbations.
- 96
- LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields76
The extensive experiments on the scene-level KITTI-360 dataset, and on the object-level NeRF-MVL show that the LiDAR-NeRF surpasses the model-based algorithms significantly, and a structural regularization method to preserve local structural details is introduced.
- 70
- 69
- Adaptively Connected Neural Networks69
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects: first, ACNet employs a flexible way to switch global and local inference in processing the internal feature representations by adaptively determining the connection status among the feature nodes.
- Solving Inefficiency of Self-supervised Representation Learning68
This paper proposes a novel self-supervised learning framework using a truncated triplet loss that demonstrates the model’s superiority over the latest state-of-the-art methods by a clear margin.
- ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency62
The text-to-views consistency modeling benefits the dense assignment of the visual features by encouraging different crops to align with the same text, while the cross-view segmentation consistency modeling provides additional self-supervision, overcoming the limitation of ambiguous text supervision for segmentation masks.
- Automated Progressive Learning for Efficient Training of Vision Transformers56
This paper proposes automated progressive learning (AutoProg), an efficient training scheme that aims to achieve lossless acceleration by automatically increasing the training overload on-the-fly; this is achieved by adaptively deciding whether, where and how much should the model grow during progressive learning.
- Beyond Fixation: Dynamic Window Visual Transformer51
The dynamic window strategy proposed by DW- ViT goes beyond the model that employs a fixed single window setting and is the first to use dynamic multi-scale windows to explore the upper limit of the effect of window settings on model performance.
- 50
- Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion48
This work proposes a novel reward-adaptive reinforcement learning method for biped locomotion, allowing the control policy to be simultaneously optimized by multiple criteria using a dynamic mechanism, leading to hybrid policy gradients.
- 45
- 45
- DARI: Distance Metric and Representation Integration for Person Verification37
This work proposes an end-to-end learning framework called DARI, i.e. Distance metric And Representation Integration, and validates the effectiveness of DARI in the challenging task of person verification.
- Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer34
The proposed Tem-adapter enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner that first designs a template to fuse question and answer pairs as event descriptions and then learns a Transformer decoder with the whole video sequence as guidance for refinement.
- Deep Structured Scene Parsing by Learning with Image Descriptions33
This paper proposes a deep architecture consisting of a convolutional neural network extracting the image representation for pixelwise object labeling and a recursive neural network discovering the hierarchical object structure and the inter-object relations and decomposes each sentence into a semantic tree.
- 29
- EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation28
This paper has a critical insight that improving the feed-forward network (FFN) in BERT has a higher gain than improving the multi-head attention (MHA) since the computational cost of FFN is 2$\sim$3 times larger than MHA.
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction27
This work proposes VTON 360, a novel 3D VTON method that addresses the open challenge of achieving high-fidelity VTON that supports any-view rendering, and leverages the equivalence between a 3D model and its rendered multi-view 2D images to reformulate 3D VTON as an extension of 2D VTON that ensures 3D consistent results across multiple views.
- A Deep Joint Learning Approach for Age Invariant Face Verification27
A new deep Convolutional Neural Network model for age-invariant face verification, which can learn features, distance metrics and threshold simultaneously simultaneously is proposed, which outperforms other state-of-the-art methods on MORPH-II database.
- 26
- AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis25
This work conducts comprehensive analyses on the multimodal implicit field of LiDAR-camera joint synthesis, revealing the underlying issue lies in the misalignment of different sensors, and introduces AlignMiF, a geometrically aligned multimodal implicit field with two proposed modules: Geometry-Aware Alignment (GAA) and Shared Geometry Initialization (SGI).
- MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation25
MixReorg is proposed, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model’s ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence.
- LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts25
This paper achieves accurate complex scene generation by proposing a semantically controllable Layout-AWare diffusion model, termed LAW-Diffusion, which introduces a spatial dependency parser to encode the location-aware semantic coherence across objects as a layout embedding and produces a scene with perceptually harmonious object styles and contextual relations.
- Kalman Normalization: Normalizing Internal Representations Across Network Layers24
A novel normalization method, called Kalman Normalization (KN), is presented, which treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering.
- Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift22
This work addresses the ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift, using a nontrivial supernet-∏ model, called ∏-NAS, which runs in an unsupervised manner, which can search for more transferable architectures.
- 18
- Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition16
This work proves that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
- 14
- 12
- 12
- Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs12
This work demonstrates that conventional neural network classifiers can generate high-quality images of a large number of categories, being comparable to the state-of-the-art generative models (e.g., DDPMs and GANs).
- Grammatically Recognizing Images with Tree Convolution11
A simple yet effective tree convolution (TreeConv) operation for deep neural networks that designs a generative image grammar, i.e., tree generation rule, to parse the hierarchy of internal feature maps by generating tree structures and implicitly learning the specific visual grammars for each object category.
- CamDrop10
A new explanation of dropout is given from the perspective of optimization that it makes the upper bound of the magnitude of gradients much tighter, which leads to a more stable behavior of the gradients and effectively avoids neurons falling into the saturation region of the nonlinear activation, even when using high learning rates.
- DNA Family: Boosting Weight-Sharing NAS With Block-Wise Supervisions7
This work modularizes a large search space into blocks with small search spaces and develops a family of models, namely a DNA family, that are capable of resolving multiple dilemmas of the weight-sharing NAS, such as scalability, efficiency, and multi-modal compatibility.
- Implicit neural representations for chemical reaction paths6
It is shown that neural networks can be optimized to represent minimum energy paths as continuous functions, offering a flexible alternative to discrete path-search methods such as Nudged Elastic Band and demonstrating promise for a universal reaction path representation.
- 6
- 6
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning5
It is substantiated that the NeRF-VPT significantly elevates baseline performance and proficiently generates more high-quality novel view images than all the compared state-of-the-art methods.
- Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing5
The traditional hypothesis-testing method is extended to a hypothesis-training-testing statistical inference method to validate the hypothesis on the weight similarity of neural networks, and experiments on several datasets consistently validated the hypothesis of weight similarity measure.
- Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation4
PhysGen (Learning Physics from Pretrained Video Generation Models), a scalable continuous and sequential world interaction framework that leverages autoregressive video generation to solve robotic manipulation tasks, is introduced.
- Language-Free Compositional Action Generation via Decoupling Refinement4
This study introduces a novel framework to generate compositional actions without language auxiliaries using a conditional generative model, CVAE, and a self-supervised pre-trained model MAE to ensure semantic consistency between sub-actions and compositional actions.
- E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion3
E 0 is introduced, a continuized discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens that supports a significantly larger and finer-grained action vocabulary and avoids the distributional mismatch introduced by masking-based corruptions—yielding more accurate fine-grained action control.
- 3
- 3
- AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment2
This paper presents AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background, and introduces two high-quality animal video datasets featuring a wide variety of species.
- 2
- Scene Parsing by Weakly Supervised Learning with Image Descriptions.2
This paper proposes a deep architecture consisting of two networks: i) a convolutional neural network extracting the image representation for pixel-wise object labeling and ii) a recursive neural network discovering the hierarchical object structure and the inter-object relations.
- OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World Modeling1
Object-Oriented World Modeling is proposed, a novel framework that structures embodied reasoning through the lens of software engineering formalisms and significantly outperforms unstructured textual baselines in planning coherence, execution success, and structural fidelity, establishing a new paradigm for structured embodied reasoning.
- HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics1
HumanGenesis achieves state-of-the-art performance on tasks including text-guided synthesis, video reenactment, and novel-pose generalization, significantly improving expressiveness, geometric fidelity, and scene integration.
- 1
- Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers1
This work reduces the search cost of AutoView to nearly zero by learning views and network parameters simultaneously in a single forward-backward step, minimizing and maximizing the mutual information among different augmented views, respectively, and proposes a self-regularized loss term to guarantee the information propagation.
- 1
- ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models–
ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains, is introduced and it is demonstrated that ReaLM significantly improves SLM performance across aspects (1)-(3) above.
- Geometry aware 3D generation from in-the-wild images in ImageNet–
A method for reconstructing 3D geometry from the diverse and unstructured Imagenet dataset without camera pose information is proposed and the class-conditional generation results demonstrate significant improvement over the current state-of-the-art method.
- –
- FNNP: Fast Neural Network Pruning Using Adaptive Batch Normalization–
This work presents a pruning method called Fast Neural Network Pruning (FNNP), in which a simple yetcient evaluation component called adaptive-BN-based evaluation is applied to unveil a strong correlation be-tween different pruned DNN structures and their settled accuracy.
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.