Search Results for author:
Found 20 papers, 5 papers with code
NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?
Multimodal Large Language Models (MLLMs) have made notable advances in visual understanding, yet their abilities to recognize objects modified by specific attributes remain an open question.
EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension
Instead of relying on large amounts of data and/or scaling up network parameters, we introduce a highly effective retrieval-augmented image captioning method that prompts LLMs with object names retrieved from External Visual--name memory (EVCap).
A-CAP: Anticipation Captioning with Commonsense Knowledge
Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time.
TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval
Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval.
SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval
To this end, we introduce a novel SHREC challenge track that focuses on retrieving relevant 3D animal models from a dataset using sketch queries and expedites accessing 3D models through available sketches.
Video Sparse Transformer With Attention-Guided Memory for Video Object Detection
In this paper, we enhance features element-wisely before the object candidate region detection, proposing Video Sparse Transformer with Attention-guided Memory (VSTAM).
Ranked #1 on
Object Detection
on UA-DETRAC
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
We propose an end-to-end Novel Object Captioning with Retrieved vocabulary from External Knowledge method (NOC-REK), which simultaneously learns vocabulary retrieval and caption generation, successfully describing novel objects outside of the training dataset.
ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding.
PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression.
Agent-Environment Network for Temporal Action Proposal Generation
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos.
Anabranch Network for Camouflaged Object Segmentation
Different from existing networks for segmentation, our proposed network possesses the second branch for classification to predict the probability of containing camouflaged object(s) in an image, which is then fused into the main branch for segmentation to boost up the segmentation accuracy.
Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion
The internal geometry of most modern consumer cameras is not adequately described by the perspective projection.
TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell
In this paper, we propose the tetrahedral outer shell volumetric truncated signed distance function (TetraTSDF) model for the human body, and its corresponding part connection network (PCN) for 3D human body shape regression.
Two-Stream FCNs to Balance Content and Style for Style Transfer
The semantic content feature and the style representation feature are then concatenated adaptively and fed into the decoder to generate style-transferred (stylized) images.
Visual-Relation Conscious Image Generation from Structured-Text
We also use individual relation separately to predict from the initial bounding-boxes relation-units for all the relations in the input text.
Linear solution to the minimal absolute pose rolling shutter problem
Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster.
Semantic Instance Meets Salient Object: Study on Video Semantic Salient Instance Segmentation
In addition, to tackle the task of VSSIS, we augment the DAVIS-2017 benchmark dataset by assigning semantic ground-truth for salient instance labels, obtaining SEmantic Salient Instance Video (SESIV) dataset.
Region growing using superpixels with learned shape prior.
Region growing is a classical image segmentation method based on hierarchical region aggregation using local similarity rules.
Video Salient Object Detection Using Spatiotemporal Deep Features
STCRF is our extension of CRF to the temporal domain and describes the relationships among neighboring regions both in a frame and over frames.
Region-Based Multiscale Spatiotemporal Saliency for Video
Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video.
