Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks78 from public data
- 4,660
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)2,522
This paper targets at learning discriminative part-informed features for person retrieval and lays emphasis on the content consistency within each part, resulting in refined parts with enhanced within-part consistency.
- MARS: A Video Benchmark for Large-Scale Person Re-Identification1,088
It is shown that CNN in classification mode can be trained from scratch using the consecutive bounding boxes of each identity, and the learned CNN embedding outperforms other competing methods considerably and has good generalization ability on other video re-id datasets upon fine-tuning.
- Person Re-identification in the Wild830
A new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, and it is shown that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement.
- SIFT Meets CNN: A Decade Survey of Instance Retrieval756
A comprehensive survey of instance retrieval over the last decade, presenting milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.
- 317
- 233
- Packing and Padding: Coupled Multi-index for Accurate Image Retrieval223
A coupled Multi-Index (c-MI) framework to perform feature fusion at indexing level, which improves the retrieval accuracy significantly, while consuming only half of the query time compared to the baseline, and is well complementary to many prior techniques.
- GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions220
A systematic framework to edit 3D scenes delicately via 3D Gaussians with text instructions, which can achieve more delicate and precise editing of 3D scenes than previous methods while enjoying much faster training speed, i.e. within 20 minutes on a single V100 GPU.
- 191
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data167
This work presents a novel hallucination detection and elimination framework, HalluciDoctor, based on the cross-checking paradigm, and uses this framework to identify and eliminate hallucinations in the training data automatically, and indicates that spurious correlations arising from long-tail object cooccurrences contribute to hallucinations.
- Discriminative coupled dictionary hashing for fast cross-media retrieval150
The experiments show that the DCDH and MV-DCDH outperform the state-of-the-art methods significantly on cross-media retrieval and conjecture that a balanced representation is crucial in cross- media retrieval.
- Building contextual visual vocabulary for large-scale image applications137
The experimental results show that the contextual visual vocabulary shows significant improvement over the classic visual vocabulary, and outperforms the state-of-the-art Bundled Feature in the terms of retrieval precision, memory consumption and efficiency.
- 131
- 130
- 122
- 105
- Home photo content modeling for personalized event-based retrieval103
This work addresses the semantic gap between feature-based indexes computed automatically and human query and retrieval preferences and addresses the need for effective tools to organize and access photos in a semantically meaningful way.
- Scalar quantization for large scale image search97
The proposed scalar quantization achieves a relatively 42% improvement in mean average precision over the baseline (hierarchical visual vocabulary tree approach), and also outperforms the state-of-the-art Hamming Embedding approach and soft assignment method.
- Accurate Image Search with Multi-Scale Contextual Evidences92
This paper proposes to integrate discriminative cues from multiple contextual levels, i.e., local, regional, and global, via probabilistic analysis, and shows that CNN feature is complementary to SIFT due to its semantic awareness and compares favorably to several other descriptors such as GIST, HSV, etc.
- 92
- 84
- Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval82
This paper proposes a Bayes merging approach to down-weight the indexed features in the intersection set through explicitly modeling the correlation problem in a probabilistic view, and a joint similarity on both image- and feature-level is estimated for the indexed Features in the intersections set.
- 79
- 71
- 70
- 65
- 58
- 56
- 55
- 51
- 49
- 47
- Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping45
This work learns and considers the contextual relations among human attributes, and validate that such cues help person re-identification tasks, and establishes a discriminative feature representation by leveraging the relations between attributes and low-level features within a latent space.
- Embedding spatial context information into inverted filefor large-scale image retrieval44
Two approaches to embed spatial context information into the inverted file are explored, one of which is to build a spatial relationship dictionary embedded with spatial context among local features, and the other is to generate a spatial context binary signature for each feature, which is called one-multiple spatial relationship method.
- 42
- 40
- Fine-residual VLAD for image retrieval40
This paper revisits the vector of locally aggregated descriptors (VLAD), which aggregates the residuals of local descriptors to their cluster centers, and proposes to generate a number of residual codebooks descended from the original clusters to generate the fine residuals.
- 37
- Exploiting Hierarchical Activations of Neural Network for Image Retrieval36
A Multi-layer Orderless Fusion (MOF) approach to integrate the activations of CNN in the Bag-of-Words (BoW) framework is proposed, through only one forward pass in the network, to extract multi-layer CNN activation of local patches.
- 36
- 36
- 35
- 30
- 29
- Toward a higher-level visual representation for object-based image retrieval27
The testing on Caltech-256 data set shows that the visual synset can partially bridge visual differences of images of the same class and deliver satisfactory retrieval of relevant images with different visual appearances.
- 25
- Exploiting local linear geometric structure for identifying correct matches24
Experimental results on several public datasets show that the proposed efficient and effective method for identifying correct matches from an initial batch of feature correspondences outperforms state-of-the-art techniques in terms of speed and accuracy.
- 22
- Scalable Image Search with Multiple Index Tables19
This paper proposes a novel approach to build multiple index tables which concurrently check for collision of the same hash values which demonstrates the indexing efficiency and retrieval accuracy of this approach.
- Context-Aware Semi-Local Feature Detector18
A context-aware semi-local detector (CASL) framework that integrates the context of interest points to recurrently refine their detections and produces more category-aware features which substantially benefits the subsequent visual categorization process.
- Towards Visual Feature Translation15
This paper proposes a Hybrid Auto-Encoder (HAE) to translate visual features, which learns a mapping by minimizing the translation and reconstruction errors, and an Undirected Affinity Measurement (UAM) is further designed to quantify the affinity among different types of visual features.
- 14
- The use of temporal, semantic and visual partitioning model for efficient near-duplicate keyframe detection in large scale news corpus12
A temporal, semantic and visual partitioning model is proposed to divide the corpus into small overlapping partitions by exploiting domain knowledge and corpus characteristics to efficiently detect NDKs in each partition separately and then link them together across partitions.
- Visual reranking with improved image graph11
An improved reranking method for the Bag-of-Words (BoW) based image search, based on a directed image graph robust to outlier distraction, which shows that the rank-level feature fusion can be adopted in this re ranking method as well.
- 7
- Salable Image Search with Reliable Binary Code7
This paper investigates the reliability of each bit in scalar quantization and proposes a novel reliable binary SIFT feature that accelerates the search speed by narrowing search space, but also improves the retrieval accuracy by alleviating the impact of unreliable quantized bits.
- Boosting Segment Anything Model Towards Open-Vocabulary Learning5
This paper introduces a novel SideFormer module designed to acquire SAM features adept at perceiving objects and inject comprehensive semantic information for recognition, and presents Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework.
- Tensor index for large scale image retrieval5
A tensor index structure to improve precision and recall simultaneously is proposed and it is shown that on the one hand, the multi-index enhances the discriminative power of visual words, thus improving precision; on the otherhand, the introduction of multiple codebooks corrects quantization artifacts, so improving recall.
- Encoding Spatial Context for Large-Scale Partial-Duplicate Web Image Retrieval5
This paper focuses on partial duplicate Web image retrieval, and proposes a scheme to encode the spatial context for visual matching verification, and an efficient affine enhancement scheme is proposed to refine the verification results.
- MultiMedia Modeling4
An algorithm that learns from uncertain data and exploits related videos for the problem of event detection; related videos are those that are closely associated, though not fully depicting the event of interest.
- Adaptively Weighted Graph Fusion for Image Retrieval4
This paper proposes an adaptively weighted graph fusion method to boost the retrieval accuracy of image retrieval by using the PageRank algorithm to analyse the linked graph and getting the corresponding PageRank value of each relevant image.
- COGE: A Novel Binary Feature Descriptor Exploring Anisotropy and Non-uniformity4
A novel COGE descriptor is introduced, a simple yet effective method for keypoint description that exploits the anisotropy and the non-uniformity of the underlying gradient distributions, which is highly discriminative and robust.
- 3
- 2
- Multimedia Content-Based Visual Retrieval2
This chapter investigates the general framework of the multimedia content-based visual retrieval, overviews the general visual search pipeline and discusses five key modules of the pipeline separately in detail.
- 2
- 2
- 1
- Improved binary feature matching through fusion of hamming distance and fragile bit weight1
A new metric, the Fragile Bit Weight (FBW), is defined, which is used in binary feature matching and measures how two features differ and can easily integrate in the well-established binary feature schemes if those descriptor bit in extract from comparison of pixels are integrated.
- A Novel Binary Feature from Intensity Difference Quantization between Random Sample of Points1
This paper proposed one kind of fast descriptor for local patch which consists of a string of binary bits derived from the intensity difference quantization (IDQ) between pixel pairs which are chosen according to a fixed random sample pattern, so it is called DIDQ (descriptor based on IDQ).
- On the Large-Scale Transferability of Convolutional Neural Networks–
This paper investigates the effective transfer of the CNN descriptors in generic and fine-grained classification at a large scale and provides some simple yet effective methods in constructing a competitive baseline recognition system.
- Scalable local feature matching without visual codebook training–
This work approaches the scalable feature matching problem with a novel perspective and address it without training visual codebook and discusses two solutions on this new paradigm, i.e., binary SIFT based quantization and dual cascaded scalar quantization.
- Hierarchical Encoding of Binary Descriptors for Image Matching–
This paper hierarchically encode the intensity differences between pixel pairs to build a discriminative binary feature and shows that the encoded descriptor is as efficient as the state-of-the-art binary descriptors in both computing and matching.
- Evaluation on the Impact of Image Quality on Image Retrieval–
A baseline system with the classic Bag-of-Visual-Words model and the inverted index structure is built and some conclusions are drawn from the evaluation results.
- –
- Robust image representation for classification and retrieval–
A new model of image representation based on a multi-layer codebook that is compact and consistent with the BoW model, which makes it applicable to image retrieval and other related task in computer vision as well.
- –
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 2026-10-15. 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.