Search Results for author:
Found 65 papers, 42 papers with code
Exploring Implicit Image Statistics for Visual Representativeness Modeling
In this paper, we propose a computational model of visual representativeness by integrating cognitive theories of representativeness heuristics with computer vision and machine learning techniques.
The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image.
GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints
In offline optimization, we adopt an end-to-end formulation, which jointly trains the visual tree parser, the structured relevance and diversity constraints, as well as the LSTM based captioning model.
Deep Saliency Hashing
As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images.
Semantic and Contrast-Aware Saliency
The two pathways characterize both long-term and short-term attention cues and are integrated dynamically using maxima normalization.
Towards Optimal Discrete Online Hashing with Balanced Similarity
In this paper, we propose a novel supervised online hashing method, termed Balanced Similarity for Online Discrete Hashing (BSODH), to solve the above problems in a unified framework.
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e. g., table legs) from different coarse 3D volumes to obtain a fused 3D volume.
Ranked #4 on
3D Object Reconstruction
on Data3D−R2N2
Hadamard Matrix Guided Online Hashing
We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code.
Supervised Online Hashing via Similarity Distribution Learning
In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.
Information Competing Process for Learning Diversified Representations
Learning representations with diversified information remains as an open problem.
Semi-Supervised Adversarial Monocular Depth Estimation
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available.
Scene-based Factored Attention for Image Captioning
Specifically, the proposed module first embeds the scene concepts into factored weights explicitly and attends the visual information extracted from the input image.
Semantic-aware Image Deblurring
Specially, we propose a novel Structured-Spatial Semantic Embedding model for image deblurring (termed S3E-Deblur), which introduces a novel Structured-Spatial Semantic tree model (S3-tree) to bridge two basic tasks in computer vision: image deblurring (ImD) and image captioning (ImC).
Deep Semantic Parsing of Freehand Sketches with Homogeneous Transformation, Soft-Weighted Loss, and Staged Learning
First, we propose a homogeneous transformation method to address the problem of domain adaptation.
Sketch-Specific Data Augmentation for Freehand Sketch Recognition
Conventional methods for this task often rely on the availability of the temporal order of sketch strokes, additional cues acquired from different modalities and supervised augmentation of sketch datasets with real images, which also limit the applicability and feasibility of these methods in real scenarios.
Toward 3D Object Reconstruction from Stereo Images
Inferring the 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem.
Hadamard Codebook Based Deep Hashing
Specifically, we utilize an off-the-shelf algorithm to generate a binary Hadamard codebook to satisfy the requirement of bit independence and bit balance, which subsequently serves as the desired outputs of the hash functions learning.
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.
Variational Structured Semantic Inference for Diverse Image Captioning
To model these two inherent diversities in image captioning, we propose a Variational Structured Semantic Inferring model (termed VSSI-cap) executed in a novel structured encoder-inferer-decoder schema.
A Real-time Global Inference Network for One-stage Referring Expression Comprehension
Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description.
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
In addition, we address a key challenge in this multi-task setup, i. e., the prediction conflict, with two innovative designs namely, Consistency Energy Maximization (CEM) and Adaptive Soft Non-Located Suppression (ASNLS).
Generalized Referring Expression Comprehension
Referring Expression
+2
Fast Class-wise Updating for Online Hashing
To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.
Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
The latter contains a Global Adaptive Controller that can adaptively fuse the global information into the decoder to guide the caption generation.
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.
Dual-Level Collaborative Transformer for Image Captioning
Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning.
RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words
Then, we build a BERTbased language model to extract language context and propose Adaptive-Attention (AA) module on top of a transformer decoder to adaptively measure the contribution of visual and language cues before making decisions for word prediction.
Towards Language-guided Visual Recognition via Dynamic Convolutions
Based on the LaConv module, we further build the first fully language-driven convolution network, termed as LaConvNet, which can unify the visual recognition and multi-modal reasoning in one forward structure.
DIFNet: Boosting Visual Information Flow for Image Captioning
Current Image captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information.
Global2Local: A Joint-Hierarchical Attention for Video Captioning
Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as their spatial-temporal correlations from the redundant frames and semantic content.
SeqTR: A Simple yet Universal Network for Visual Grounding
In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e. g., phrase localization, referring expression comprehension (REC) and segmentation (RES).
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
Extensive experiments on HICO-Det dataset demonstrate that our model discovers potential interactive pairs and enables the recognition of unseen HOIs.
Human-Object Interaction Detection
Knowledge Distillation
+4
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost.
A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension
But the most encouraging finding is that with much less training overhead and parameters, SimREC can still achieve better performance than a set of large-scale pre-trained models, e. g., UNITER and VILLA, portraying the special role of REC in existing V&L research.
X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval
However, cross-grained contrast, which is the contrast between coarse-grained representations and fine-grained representations, has rarely been explored in prior research.
Ranked #12 on
Video Retrieval
on MSVD
Clover: Towards A Unified Video-Language Alignment and Fusion Model
We then introduce \textbf{Clover}\textemdash a Correlated Video-Language pre-training method\textemdash towards a universal Video-Language model for solving multiple video understanding tasks with neither performance nor efficiency compromise.
Ranked #1 on
Video Question Answering
on LSMDC-FiB
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized change of training loss when adding a perturbation to the weight.
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension
In this paper, we present the first attempt of semi-supervised learning for REC and propose a strong baseline method called RefTeacher.
RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension
Based on RefCLIP, we further propose the first model-agnostic weakly supervised training scheme for existing REC models, where RefCLIP acts as a mature teacher to generate pseudo-labels for teaching common REC models.
Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network
Extensive experiments on the PNG benchmark dataset demonstrate the effectiveness and efficiency of our method.
Towards Local Visual Modeling for Image Captioning
In this paper, we study the local visual modeling with grid features for image captioning, which is critical for generating accurate and detailed captions.
Towards Efficient Visual Adaption via Structural Re-parameterization
Experimental results show the superior performance and efficiency of RepAdapter than the state-of-the-art PETL methods.
Towards End-to-end Semi-supervised Learning for One-stage Object Detection
In addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively.
Active Teacher for Semi-Supervised Object Detection
In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github. com/HunterJ-Lin/ActiveTeacher}) for semi-supervised object detection (SSOD).
X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance
Text-driven 3D stylization is a complex and crucial task in the fields of computer vision (CV) and computer graphics (CG), aimed at transforming a bare mesh to fit a target text.
Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
To validate MMA, we apply it to a recent LLM called LLaMA and term this formed large vision-language instructed model as LaVIN.
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks.
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight.
Towards General Visual-Linguistic Face Forgery Detection
To address this issues, in this paper, we propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation
Insufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space, rather than independently aligning with each modality.
Continual Face Forgery Detection via Historical Distribution Preserving
In this paper, we focus on a novel and challenging problem: Continual Face Forgery Detection (CFFD), which aims to efficiently learn from new forgery attacks without forgetting previous ones.
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions.
JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues
The rising importance of 3D understanding, pivotal in computer vision, autonomous driving, and robotics, is evident.
NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning
To address this, we introduce two cascading modules based on the barycenter of the mask, which are Coordinate Guided Aggregation (CGA) and Barycenter Driven Localization (BDL), responsible for segmentation and detection, respectively.
Semi-Supervised Panoptic Narrative Grounding
Remarkably, our SS-PNG-NW+ outperforms fully-supervised models with only 30% and 50% supervision data, exceeding their performance by 0. 8% and 1. 1% respectively.
Towards Omni-supervised Referring Expression Segmentation
To address this issue, we propose a new learning task for RES called Omni-supervised Referring Expression Segmentation (Omni-RES), which aims to make full use of unlabeled, fully labeled and weakly labeled data, e. g., referring points or grounding boxes, for efficient RES training.
X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation
Nevertheless, a substantial domain gap exists between 2D images and 3D assets, primarily attributed to variations in camera-related attributes and the exclusive presence of foreground objects.
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries.
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
In particular, InstDiffEdit aims to employ the cross-modal attention ability of existing diffusion models to achieve instant mask guidance during the diffusion steps.
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a combination of low- and high-resolution visual features can effectively mitigate this shortcoming.
Ranked #55 on
Visual Question Answering
on MM-Vet
Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization
Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor quality.
Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models
In this paper, we propose a novel parameter and computation efficient tuning method for Multi-modal Large Language Models (MLLMs), termed Efficient Attention Skipping (EAS).
DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis
The rapid progress in deep learning has given rise to hyper-realistic facial forgery methods, leading to concerns related to misinformation and security risks.
Deep Instruction Tuning for Segment Anything Model
Segment Anything Model (SAM) exhibits powerful yet versatile capabilities on (un) conditional image segmentation tasks recently.
