Search Results for author:
Found 67 papers, 37 papers with code
Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
To tackle this, we introduce a new metric called Balancing Preservation and Modification (BPM), tailored for instruction-based image editing by explicitly disentangling the image into editing-relevant and irrelevant regions for specific consideration.
PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation
To further explore PosterO's abilities under the generalized settings, we built PStylish7, the first dataset with multi-purpose posters and various-shaped elements, further offering a challenging test for advanced research.
DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
Humans can effortlessly locate desired objects in cluttered environments, relying on a cognitive mechanism known as visual search to efficiently filter out irrelevant information and focus on task-related regions.
Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention.
ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer
The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage.
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts, but they typically rely on a single static prompt for all video sequences, overlooking the diverse temporal dynamics and spatial variations that exist across frames.
SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
To address these limitations, we propose a novel transductive TTA framework, Supportive Clique-based Attribute Prompting (SCAP), which effectively combines visual and textual information to enhance adaptation by generating fine-grained attribute prompts across test batches.
Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks.
DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification
However, due to the long-term nature of lifelong learning, the inevitable changes in human clothes prevent the model from relying on unified discriminative information (e. g., clothing style) to match the same person in the streaming data, demanding differentiated cloth-irrelevant information.
Selective Visual Prompting in Vision Mamba
To prevent the loss of discriminative information during state space propagation, SVP employs lightweight selective prompters for token-wise prompt generation, ensuring adaptive activation of the update and forget gates within Mamba blocks to promote discriminative information propagation.
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification
To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong anti-forgetting capacity without storing any exemplars.
CountMamba: Exploring Multi-directional Selective State-Space Models for Plant Counting
Plant counting is essential in every stage of agriculture, including seed breeding, germination, cultivation, fertilization, pollination yield estimation, and harvesting.
Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation
Recommendation models utilizing unique identities (IDs) to represent distinct users and items have dominated the recommender systems literature for over a decade.
SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
To mitigate the inaccurate region classification in OVD, we propose a new Shape-Invariant Adapter named SIA-OVD to bridge the image-region gap in the OVD task.
Ranked #10 on
Open Vocabulary Object Detection
on MSCOCO
SIM-OFE: Structure Information Mining and Object-aware Feature Enhancement for Fine-Grained Visual Categorization
To address the above issue, we propose a Structure Information Mining and Object-aware Feature Enhancement (SIM-OFE) method for finegrained visual categorization, which explores the visual object’s internal structure composition and appearance traits.
Ranked #5 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
Training-free Video Temporal Grounding using Large-scale Pre-trained Models
In this paper, we propose a Training-Free Video Temporal Grounding (TFVTG) approach that leverages the ability of pre-trained large models.
ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding
This method generates additional training data by synthesizing images containing multiple objects of the same category and pseudo queries based on their spatial relationships.
Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection
This approach enhances the generalization of large foundation models, such as CLIP, when fine-tuned for HOI detection.
FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment
We argue that a fine-grained understanding of actions requires the model to perceive and parse actions in both time and space, which is also the key to the credibility and interpretability of the AQA technique.
Ranked #2 on
Action Quality Assessment
on FineDiving
FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models
We further extend FinePOSE to multi-human pose estimation.
FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding
Fine-grained action analysis in multi-person sports is complex due to athletes' quick movements and intense physical confrontations which result in severe visual obstructions in most scenes.
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
Then the Distribution-oriented Prototype Generation algorithm transforms the instance-level diversity into identity-level distributions as prototypes which is further explored by the designed Prototype-based Knowledge Transfer module to enhance the knowledge anti-forgetting and acquisition capacity of the LReID model.
FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning
Non-Exemplar Class Incremental Learning (NECIL) involves learning a classification model on a sequence of data without access to exemplars from previously encountered old classes.
Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
To this end we propose a Continual Compatible Representation (C2R) method which facilitates the query feature calculated by the continuously updated model to effectively retrieve the gallery feature calculated by the old model in a compatible manner.
Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval
Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i. e., the same sub-category labels) highest based on the fine-grained details in the query.
Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory
This observation motivates us to design an HOI detector that can be trained even with long-tailed labeled data and can leverage existing knowledge from pre-trained models.
Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model
In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e. g., language descriptions and synchronous audios.
MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-behavior Recommendation
In this paper, we propose MB-HGCN, a novel multi-behavior recommendation model that uses a hierarchical graph convolutional network to learn user and item embeddings from coarse-grained on the global level to fine-grained on the behavior-specific level.
Multi-Behavior Recommendation with Cascading Graph Convolution Networks
Most existing multi-behavior models fail to capture such dependencies in a behavior chain for embedding learning.
PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design.
Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos
Video temporal grounding aims to pinpoint a video segment that matches the query description.
Confidence-aware Pseudo-label Learning for Weakly Supervised Visual Grounding
Visual grounding aims at localizing the target object in image which is most related to the given free-form natural language query.
Masked Retraining Teacher-Student Framework for Domain Adaptive Object Detection
This helps the student model capture target domain characteristics and become a more data-efficient learner to gain knowledge from the limited number of pseudo boxes.
An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data.
SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization
To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object structure information into transformer for enhancing discriminative representation learning to contain both the appearance information and structure information.
Team PKU-WICT-MIPL PIC Makeup Temporal Video Grounding Challenge 2022 Technical Report
In this technical report, we briefly introduce the solutions of our team `PKU-WICT-MIPL' for the PIC Makeup Temporal Video Grounding (MTVG) Challenge in ACM-MM 2022.
Disentangled Graph Neural Networks for Session-based Recommendation
The session embedding is then generated by aggregating the item embeddings with attention weights of each item's factors.
Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning
Moreover, they train their model to distinguish positive visual-language pairs from negative ones randomly collected from other videos, ignoring the highly confusing video segments within the same video.
Ranked #8 on
Temporal Sentence Grounding
on Charades-STA
Fine-Grained Image Analysis with Deep Learning: A Survey
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.
A New Benchmark and Approach for Fine-grained Cross-media Retrieval
To the best of our knowledge, it is the first benchmark with 4 media types for fine-grained cross-media retrieval.
Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning
The main novelties and advantages are: (1) Bidirectional temporal graph: A bidirectional temporal graph is constructed along and reversely along the temporal order, which provides complementary ways to capture the temporal trajectories for each salient object.
Text-to-image Synthesis via Symmetrical Distillation Networks
For addressing these problems, we exploit the excellent capability of generic discriminative models (e. g. VGG19), which can guide the training process of a new generative model on multiple levels to bridge the two gaps.
Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification
Video representation learning is a vital problem for classification task.
Visual Data Synthesis via GAN for Zero-Shot Video Classification
First, we propose multi-level semantic inference to boost video feature synthesis, which captures the discriminative information implied in joint visual-semantic distribution via feature-level and label-level semantic inference.
Cross-media Multi-level Alignment with Relation Attention Network
First, we propose visual-language relation attention model to explore both fine-grained patches and their relations of different media types.
Deep Cross-media Knowledge Transfer
For achieving the goal, this paper proposes deep cross-media knowledge transfer (DCKT) approach, which transfers knowledge from a large-scale cross-media dataset to promote the model training on another small-scale cross-media dataset.
Multimedia
SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
(2) Ignore the rich information contained in the large amount of unlabeled data across different modalities, especially the margin examples that are easily to be incorrectly retrieved, which can help to model the correlations.
Deep Reinforcement Learning for Image Hashing
Inspired by the sequential decision ability of deep reinforcement learning, we propose a new Deep Reinforcement Learning approach for Image Hashing (DRLIH).
Unsupervised Generative Adversarial Cross-modal Hashing
To address the above problem, in this paper we propose an Unsupervised Generative Adversarial Cross-modal Hashing approach (UGACH), which makes full use of GAN's ability for unsupervised representation learning to exploit the underlying manifold structure of cross-modal data.
Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification
Recently, researchers generally adopt the deep networks to capture the static and motion information \textbf{\emph{separately}}, which mainly has two limitations: (1) Ignoring the coexistence relationship between spatial and temporal attention, while they should be jointly modelled as the spatial and temporal evolutions of video, thus discriminative video features can be extracted.
CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
They can not only exploit cross-modal correlation for learning common representation, but also preserve reconstruction information for capturing semantic consistency within each modality.
Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
Therefore, we propose a weakly supervised discriminative localization approach (WSDL) for fast fine-grained image classification to address the two limitations at the same time, and its main advantages are: (1) n-pathway end-to-end discriminative localization network is designed to improve classification speed, which simultaneously localizes multiple different discriminative regions for one image to boost classification accuracy, and shares full-image convolutional features generated by region proposal network to accelerate the process of generating region proposals as well as reduce the computation of convolutional operation.
Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
Existing methods generally adopt a two-stage learning framework: The first stage is to localize the discriminative regions of objects, and the second is to encode the discriminative features for training classifiers.
Fine-grained Visual-textual Representation Learning
As is known to all, when we describe the object of an image via textual descriptions, we mainly focus on the pivotal characteristics, and rarely pay attention to common characteristics as well as the background areas.
Modality-specific Cross-modal Similarity Measurement with Recurrent Attention Network
Effectively measuring the similarity between different modalities of data is the key of cross-modal retrieval.
MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval
Transfer learning is for relieving the problem of insufficient training data, but it mainly focuses on knowledge transfer only from large-scale datasets as single-modal source domain to single-modal target domain.
Fine-Grained Image Classification via Combining Vision and Language
Most existing fine-grained image classification methods generally learn part detection models to obtain the semantic parts for better classification accuracy.
Cross-modal Common Representation Learning by Hybrid Transfer Network
Knowledge in source domain cannot be directly transferred to both two different modalities in target domain, and the inherent cross-modal correlation contained in target domain provides key hints for cross-modal retrieval which should be preserved during transfer process.
Cross-media Similarity Metric Learning with Unified Deep Networks
Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework.
Fine-graind Image Classification via Combining Vision and Language
Most existing fine-grained image classification methods generally learn part detection models to obtain the semantic parts for better classification accuracy.
Object-Part Attention Model for Fine-grained Image Classification
Both are jointly employed to exploit the subtle and local differences for distinguishing the subcategories.
Saliency-guided video classification via adaptively weighted learning
Then two streams of 3D CNN are trained individually for raw frames and optical flow on salient areas, and another 2D CNN is trained for raw frames on non-salient areas.
Cross-modal Deep Metric Learning with Multi-task Regularization
The quadruplet ranking loss can model the semantically similar and dissimilar constraints to preserve cross-modal relative similarity ranking information.
Query-adaptive Image Retrieval by Deep Weighted Hashing
On the other hand, different hash bits actually contribute to the image retrieval differently, and treating them equally greatly affects the retrieval accuracy of image.
SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval
(2) A semi-supervised deep hashing network is designed to extensively exploit both labeled and unlabeled data, in which we propose an online graph construction method to benefit from the evolving deep features during training to better capture semantic neighbors.
The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts.
Exhaustive and Efficient Constraint Propagation: A Semi-Supervised Learning Perspective and Its Applications
This paper presents a novel pairwise constraint propagation approach by decomposing the challenging constraint propagation problem into a set of independent semi-supervised learning subproblems which can be solved in quadratic time using label propagation based on k-nearest neighbor graphs.
