Search Results for author:
Found 22 papers, 14 papers with code
Laying the Foundations of Deep Long-Term Crowd Flow Prediction
Predicting the crowd behavior in complex environments is a key requirement for crowd and disaster management, architectural design, and urban planning.
CASIM: Composite Aware Semantic Injection for Text to Motion Generation
Recent advances in generative modeling and tokenization have driven significant progress in text-to-motion generation, leading to enhanced quality and realism in generated motions.
Unifying Specialized Visual Encoders for Video Language Models
Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge.
ViUniT: Visual Unit Tests for More Robust Visual Programming
In our framework, a unit test is represented as a novel image and answer pair meant to verify the logical correctness of a program produced for a given query.
xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames.
Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization
In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data.
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions.
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs.
Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos
This knowledge, sourced from training procedure plans and structured as a directed weighted graph, equips the agent to better navigate the complexities of step sequencing and its potential variations.
Learning from Synthetic Human Group Activities
The study of complex human interactions and group activities has become a focal point in human-centric computer vision.
M3Act: Learning from Synthetic Human Group Activities
The study of complex human interactions and group activities has become a focal point in human-centric computer vision.
Procedure-Aware Pretraining for Instructional Video Understanding
This graph can then be used to generate pseudo labels to train a video representation that encodes the procedural knowledge in a more accessible form to generalize to multiple procedure understanding tasks.
MSI: Maximize Support-Set Information for Few-Shot Segmentation
To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a support mask.
Ranked #3 on
Few-Shot Semantic Segmentation
on FSS-1000 (1-shot)
HM: Hybrid Masking for Few-Shot Segmentation
A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects.
Ranked #5 on
Few-Shot Semantic Segmentation
on FSS-1000 (1-shot)
D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning
Digraph Representation Learning (DRL) aims to learn representations for directed homogeneous graphs (digraphs).
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects.
Ranked #2 on
Group Activity Recognition
on Collective Activity
Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
We evaluate over CATER dataset and find that Hopper achieves 73. 2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames.
Ranked #5 on
Video Object Tracking
on CATER
Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplans
We present a floorplan embedding technique that uses an attributed graph to represent the geometric information as well as design semantics and behavioral features of the inhabitants as node and edge attributes.
GitEvolve: Predicting the Evolution of GitHub Repositories
Given its crucial role, there is a need to better understand and model the dynamics of GitHub as a social platform.
Understanding Echo Chambers in E-commerce Recommender Systems
Current research on recommender systems mostly focuses on matching users with proper items based on user interests.
HID: Hierarchical Multiscale Representation Learning for Information Diffusion
In this paper, we present a Hierarchical Information Diffusion (HID) framework by integrating user representation learning and multiscale modeling.
Deep Crowd-Flow Prediction in Built Environments
In this paper, we propose an approach to instantly predict the long-term flow of crowds in arbitrarily large, realistic environments.
