Search Results for author:
Found 20 papers, 9 papers with code
A Systematic Survey of Automatic Prompt Optimization Techniques
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks.
Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
Despite the growing interest in Mamba architecture as a potential replacement for Transformer architecture, parameter-efficient fine-tuning (PEFT) approaches for Mamba remain largely unexplored.
Diffusion Model Patching via Mixture-of-Prompts
We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters.
RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models
By integrating the probability distributions from both the original and transformed images, RITUAL effectively reduces hallucinations.
Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
This study addresses the issue observed in Large Vision Language Models (LVLMs), where excessive attention on a few image tokens, referred to as blind tokens, leads to hallucinatory responses in tasks requiring fine-grained understanding of visual objects.
Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition
The first pathway of the relation module, the actor-centric path, initially captures the temporal dynamics of individual actors and then constructs inter-actor relationships.
Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition
Panoramic Activity Recognition (PAR) seeks to identify diverse human activities across different scales, from individual actions to social group and global activities in crowded panoramic scenes.
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation.
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
This work introduces HarmonyView, a simple yet effective diffusion sampling technique adept at decomposing two intricate aspects in single-image 3D generation: consistency and diversity.
Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition
CFEM incorporates sepearte learnable query embeddings for each modality, which guide CFEM to extract complementary information and global action content from the other modalities.
Denoising Task Routing for Diffusion Models
Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL).
Audio-Visual Glance Network for Efficient Video Recognition
To address this issue, we propose Audio-Visual Glance Network (AVGN), which leverages the commonly available audio and visual modalities to efficiently process the spatio-temporally important parts of a video.
Sketch-based Video Object Localization
We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.
Towards Good Practices for Missing Modality Robust Action Recognition
We ask: how can we train a model that is robust to missing modalities?
Temporal Flow Mask Attention for Open-Set Long-Tailed Recognition of Wild Animals in Camera-Trap Images
Camera traps, unmanned observation devices, and deep learning-based image recognition systems have greatly reduced human effort in collecting and analyzing wildlife images.
Modality Mixer for Multi-modal Action Recognition
In multi-modal action recognition, it is important to consider not only the complementary nature of different modalities but also global action content.
Impact of representation matching with neural machine translation
Most neural machine translation models are implemented as a conditional language model framework composed of encoder and decoder models.
Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos
To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.
What and When to Look?: Temporal Span Proposal Network for Video Relation Detection
TSPN tells when to look: it simultaneously predicts start-end timestamps (i. e., temporal spans) and categories of the all possible relations by utilizing full video context.
Ranked #2 on
Video Visual Relation Detection
on ImageNet-VidVRD
Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed.
Ranked #1 on
Predicate Classification
on Visual Genome
(R@100 metric)
