Search Results for author:
Found 46 papers, 15 papers with code
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
Extensive experiments on MARS-Bench also reveal that closed-source LLMs significantly outperform open-source alternatives, explicit reasoning significantly boosts LLMs' robustness on handling long complex dialogue sessions, and LLMs indeed face significant challenges when handling motivation transfer and sophisticated cross-turn dependency.
Your Classifier Can Do More: Towards Bridging the Gaps in Classification, Robustness, and Generation
To address this question, we systematically analyze the energy distribution differences of clean, adversarial, and generated samples across various JEM variants and adversarially trained models.
Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning
The lack of a Unified Face Attack Detection model to handle both types of attacks is mainly due to two factors.
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
However, existing weakly supervised image manipulation methods overlook the importance of edge information for accurate localization, leading to suboptimal localization performance.
UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery
In response, we propose UNICL-SAM, to better model the example distribution and extract robust representations to help in-context segmentation.
Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection
In this paper, we present the solutions from the top 3 teams of the two tracks, to boost the research work in the field of image and audio-video forgery detection.
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
We observe performance dips in question-answering benchmarks after the removal or expansion of the shallow layers, and the degradation shrinks as the layer gets deeper, indicating that the shallow layers hold the key to knowledge injection.
Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization
The FUP integrates detection and localization tasks using a token learning strategy and multiple forgery-aware transformers, which facilitates the use of classification information to enhance localization capability.
Transformer based Pluralistic Image Completion with Reduced Information Loss
The indices of quantized pixels are used as tokens for the inputs and prediction targets of the transformer.
Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval
Nonetheless, the method of employing a general large language model for reliable relevance judgments in legal case retrieval is yet to be thoroughly explored.
MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection
By aggregating the visual word and visual sentence features, our MiM-ISTD can effectively explore both global and local information.
Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
This bidirectional interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations.
TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection
We abstract this process as the directional movement of feature map pixels to target areas through convolution, pooling and interactions with surrounding pixels, which can be analogous to the movement of thermal particles constrained by surrounding variables and particles.
Towards More Unified In-context Visual Understanding
Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines.
GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.
Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding
Existing methods for multi-modal manipulation detection and grounding primarily focus on fusing vision-language features to make predictions, while overlooking the importance of modality-specific features, leading to sub-optimal results.
MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans.
EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors
Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space.
Ranked #101 on
3D Human Pose Estimation
on Human3.6M
Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal
Inspired by the various successful applications of large-scale pre-trained models (e. g, CLIP), in this paper, we explore the potential benefits of them for this task through both spatial feature representation learning and semantic information embedding aspects: 1) for spatial feature representation learning, we design a Spatially-Adaptive Residual (\textbf{SAR}) Encoder to extract degraded areas adaptively.
Multi-spectral Class Center Network for Face Manipulation Detection and Localization
To this end, a novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization.
Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification
Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID).
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
We demonstrate for the first time that using a text2image model to generate images or zero-shot recognition model to filter noisily crawled images for different object categories is a feasible way to make Copy-Paste truly scalable.
Ranked #8 on
Instance Segmentation
on LVIS v1.0 val
UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection
UPCL is designed for learning the consistency-related representation with progressive optimized pseudo annotations.
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task.
Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learning
Existing face forgery detection methods usually treat face forgery detection as a binary classification problem and adopt deep convolution neural networks to learn discriminative features.
Reduce Information Loss in Transformers for Pluralistic Image Inpainting
The indices of quantized pixels are used as tokens for the inputs and prediction targets of transformer.
Ranked #6 on
Seeing Beyond the Visible
on KITTI360-EX
Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector.
Ranked #7 on
Multi-Object Tracking
on MOT16
(using extra training data)
Unsupervised Finetuning
This problem is more challenging than the supervised counterpart, as the low data density in the small-scale target data is not friendly for unsupervised learning, leading to the damage of the pretrained representation and poor representation in the target domain.
Temporal RoI Align for Video Object Recognition
In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity.
Ranked #1 on
Video Instance Segmentation
on YouTube-VIS
ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation
Third, we compute the similarities between each pixel representation and the image-level contextual information, the semantic-level contextual information, respectively.
Mining Contextual Information Beyond Image for Semantic Segmentation
To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations.
Abnormal Behavior Detection Based on Target Analysis
To this end, we propose a multivariate fusion method that analyzes each target through three branches: object, action and motion.
Cascaded Residual Density Network for Crowd Counting
Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes.
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
3D Object Detection From Monocular Images
Depth Estimation
+3
Improve Unsupervised Pretraining for Few-label Transfer
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets.
Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature
Over the past several years, in order to solve the problem of malicious abuse of facial manipulation technology, face manipulation detection technology has obtained considerable attention and achieved remarkable progress.
Diverse Semantic Image Synthesis via Probability Distribution Modeling
In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level.
Ranked #1 on
Image-to-Image Translation
on Deep-Fashion
First demonstration of early warning gravitational wave alerts
We present results from an end-to-end mock data challenge that detects binary neutron star mergers and alerts partner facilities before merger.
High Energy Astrophysical Phenomena
Are Fewer Labels Possible for Few-shot Learning?
We conduct experiments on 10 different few-shot target datasets, and our average few-shot performance outperforms both vanilla inductive unsupervised transfer and supervised transfer by a large margin.
Efficient Semantic Image Synthesis via Class-Adaptive Normalization
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away.
MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing
In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation.
Rethinking Spatially-Adaptive Normalization
Despite its impressive performance, a more thorough understanding of the true advantages inside the box is still highly demanded, to help reduce the significant computation and parameter overheads introduced by these new structures.
Density-Aware Graph for Deep Semi-Supervised Visual Recognition
Motivated by these limitations, this paper proposes to solve the SSL problem by building a novel density-aware graph, based on which the neighborhood information can be easily leveraged and the feature learning and label propagation can also be trained in an end-to-end way.
Cross-modality Person re-identification with Shared-Specific Feature Transfer
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
The visibility map of the target is learned and used for inferring the spatial attention map.
