Search Results for author:
Found 46 papers, 20 papers with code
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes.
Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame.
UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track
Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video.
Referring Video Object Segmentation
Semantic Segmentation
+1
A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks
Model Inversion (MI) attacks aim to reconstruct privacy-sensitive training data from released models by utilizing output information, raising extensive concerns about the security of Deep Neural Networks (DNNs).
CLIP-Guided Networks for Transferable Targeted Attacks
Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios.
Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
We discover that the domain gap between the VLM features (e. g., CLIP) and the instance queries and the underutilization of temporal consistency are two central causes.
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments.
Hierarchical Features Matter: A Deep Exploration of GAN Priors for Improved Dataset Distillation
Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy.
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
To this end, we revisit the multimodal alignments in VLP model training and propose the Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC).
3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation
The current RVOS methods typically use independently pre-trained vision and language models as backbones, resulting in a significant domain gap between video and text.
Referring Video Object Segmentation
Semantic Segmentation
+2
GI-NAS: Boosting Gradient Inversion Attacks through Adaptive Neural Architecture Search
In this paper, we further exploit such implicit prior knowledge by proposing Gradient Inversion via Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures.
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
We find that existing LLMs, including GPT-4 and open-source LLMs specifically fine-tuned for tool use, only reach a correctness rate in the range of 30% to 60%, far from reliable use in practice.
Inverse Optimal Control for Linear Quadratic Tracking with Unknown Target States
A computationally efficient and numerically reliable parameter identification algorithm is proposed by equating optimal control strategies with a system of linear equations, and the associated relative error upper bound is derived in terms of data volume and signal-to-noise ratio.
Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing access to the trained models, have emerged as a formidable privacy threat.
Unified Physical-Digital Face Attack Detection
These three modules seamlessly form a robust unified attack detection framework.
Co-audit: tools to help humans double-check AI-generated content
Hence, we are seeing the emergence of tool-assisted experiences to help the user double-check a piece of AI-generated content.
SCREWS: A Modular Framework for Reasoning with Revisions
To enable exploration in this space, we present SCREWS, a modular framework for reasoning with revisions.
Few-Shot Adaptation for Parsing Contextual Utterances with LLMs
We evaluate the ability of semantic parsers based on large language models (LLMs) to handle contextual utterances.
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.
Natural Language Decomposition and Interpretation of Complex Utterances
Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations.
Surveillance Face Presentation Attack Detection Challenge
Based on this dataset and protocol-$3$ for evaluating the robustness of the algorithm under quality changes, we organized a face presentation attack detection challenge in surveillance scenarios.
Surveillance Face Anti-spoofing
In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks.
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering
Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular.
Unified Control Framework for Real-Time Interception and Obstacle Avoidance of Fast-Moving Objects with Diffusion Variational Autoencoder
Real-time interception of fast-moving objects by robotic arms in dynamic environments poses a formidable challenge due to the need for rapid reaction times, often within milliseconds, amidst dynamic obstacles.
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding
Satisfying these constraints simultaneously is difficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation.
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows.
Salient Object Ranking with Position-Preserved Attention
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers.
Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease
Speech disorders often occur at the early stage of Parkinson's disease (PD).
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph.
RESA: Recurrent Feature-Shift Aggregator for Lane Detection
Lane detection is one of the most important tasks in self-driving.
Ranked #5 on
Lane Detection
on TuSimple
Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects
Converting point clouds generated by Laser scanning, multiview stereo imagery or depth cameras into compact polygon meshes is a challenging problem in vision.
Building A User-Centric and Content-Driven Socialbot
Additionally, we construct a new knowledge base to power the socialbot by collecting social chat content from a variety of sources.
Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation
Data sharing for medical research has been difficult as open-sourcing clinical data may violate patient privacy.
A Dynamic Speaker Model for Conversational Interactions
Characterizing these differences can be useful in human-computer interaction, as well as analysis of human-human conversations.
Planar Shape Detection at Structural Scales
Interpreting 3D data such as point clouds or surface meshes depends heavily on the scale of observation.
Sounding Board: A User-Centric and Content-Driven Social Chatbot
We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
A Factored Neural Network Model for Characterizing Online Discussions in Vector Space
We develop a novel factored neural model that learns comment embeddings in an unsupervised way leveraging the structure of distributional context in online discussion forums.
Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement.
Bi-directional Attention with Agreement for Dependency Parsing
We develop a novel bi-directional attention model for dependency parsing, which learns to agree on headword predictions from the forward and backward parsing directions.
Ranked #4 on
Chinese Dependency Parsing
on Chinese Pennbank
Talking to the crowd: What do people react to in online discussions?
This paper addresses the question of how language use affects community reaction to comments in online discussion forums, and the relative importance of the message vs. the messenger.
Language Models for Image Captioning: The Quirks and What Works
Two recent approaches have achieved state-of-the-art results in image captioning.
Microsoft COCO Captions: Data Collection and Evaluation Server
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
From Captions to Visual Concepts and Back
The language model learns from a set of over 400, 000 image descriptions to capture the statistics of word usage.
Ranked #1 on
Image Captioning
on COCO Captions test
