19 citations · 60 across the 28 of their papers we have counts for
29 papers
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
Anindya Mondal, Sauradip Nag, Anjan Dutta
We present ABACUS, a unified vision-language model that jointly addresses object counting, crowd counting, referring-expression counting, and count-faithful image generation within…
Functionalization via Structure Completion and Motion Rectification
Mingrui Zhao, Sai Raj Kishore Perla, Kai Wang +8
Acquisition and creation of 3D assets have been largely view- or appearance-driven. As a result, existing digital 3D models often lack the requisite structural components to functi…
RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
Silpa Vadakkeeveetil Sreelatha, Sauradip Nag, Muhammad Awais +2
The rapid advancement of diffusion models has enabled high-fidelity and semantically rich text-to-image generation; however, ensuring fairness and safety remains an open challenge.…
Advances in 4D Representation: Geometry, Motion, and Interaction
Mingrui Zhao, Sauradip Nag, Kai Wang +5
We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics whose developments have been propelled by recent advances in neural fields, g…
ASIA: Adaptive 3D Segmentation using Few Image Annotations
Sai Raj Kishore Perla, Aditya Vora, Sauradip Nag +2
We introduce ASIA (Adaptive 3D Segmentation using few Image Annotations), a novel framework that enables segmentation of possibly non-semantic and non-text-describable "parts" in 3…
CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance
Anindya Mondal, Ayan Banerjee, Sauradip Nag +3
Diffusion models excel at photorealistic synthesis but struggle with object count fidelity, especially in high-density settings. We introduce COUNTLOOP, a training-free framework t…
Cora: Correspondence-aware image editing using few step diffusion
Amirhossein Alimohammadi, Aryan Mikaeili, Sauradip Nag +3
Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring sign…
In-2-4D: Inbetweening from Two Single-View Images to 4D Generation
Sauradip Nag, Daniel Cohen-Or, Hao Zhang +1
We pose a new problem, In-2-4D, for generative 4D (i.e., 3D + motion) inbetweening to interpolate two single-view images. In contrast to video/4D generation from only text or a sin…
Articulate That Object Part (ATOP): 3D Part Articulation via Text and Motion Personalization
Aditya Vora, Sauradip Nag, Kai Wang +1
We present ATOP (Articulate That Object Part), a novel few-shot method based on motion personalization to articulate a static 3D object with respect to a part and its motion as pre…
SMITE: Segment Me In TimE
Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki +3
Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty incre…
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors
Anindya Mondal, Sauradip Nag, Xiatian Zhu +1
Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adapta…
Adaptive-Labeling for Enhancing Remote Sensing Cloud Understanding
Jay Gala, Sauradip Nag, Huichou Huang +2
Cloud analysis is a critical component of weather and climate science, impacting various sectors like disaster management. However, achieving fine-grained cloud analysis, such as c…
DiffSED: Sound Event Detection with Denoising Diffusion
Swapnil Bhosale, Sauradip Nag, Diptesh Kanojia +2
Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the spl…
Actor-agnostic Multi-label Action Recognition with Multi-modal Query
Anindya Mondal, Sauradip Nag, Joaquin M Prada +2
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estim…
DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion
Sauradip Nag, Xiatian Zhu, Jiankang Deng +2
We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals…
PersonalTailor: Personalizing 2D Pattern Design from 3D Garment Point Clouds
Sauradip Nag, Anran Qi, Xiatian Zhu +1
Garment pattern design aims to convert a 3D garment to the corresponding 2D panels and their sewing structure. Existing methods rely either on template fitting with heuristics and…
Post-Processing Temporal Action Detection
Sauradip Nag, Xiatian Zhu, Yi-Zhe Song +1
Existing Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequenc…
Multi-Modal Few-Shot Temporal Action Detection
Sauradip Nag, Mengmeng Xu, Xiatian Zhu +4
Few-shot (FS) and zero-shot (ZS) learning are two different approaches for scaling temporal action detection (TAD) to new classes. The former adapts a pretrained vision model to a…
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
Sauradip Nag, Xiatian Zhu, Yi-Zhe Song +1
Existing temporal action detection (TAD) methods rely on generating an overwhelmingly large number of proposals per video. This leads to complex model designs due to proposal gener…
Large-Scale Product Retrieval with Weakly Supervised Representation Learning
Xiao Han, Kam Woh Ng, Sauradip Nag +1
Large-scale weakly supervised product retrieval is a practically useful yet computationally challenging problem. This paper introduces a novel solution for the eBay Visual Search C…
Zero-Shot Temporal Action Detection via Vision-Language Prompting
Sauradip Nag, Xiatian Zhu, Yi-Zhe Song +1
Existing temporal action detection (TAD) methods rely on large training data including segment-level annotations, limited to recognizing previously seen classes alone during infere…
Semi-Supervised Temporal Action Detection with Proposal-Free Masking
Sauradip Nag, Xiatian Zhu, Yi-Zhe Song +1
Existing temporal action detection (TAD) methods rely on a large number of training data with segment-level annotations. Collecting and annotating such a training set is thus highl…
How Far Can I Go ? : A Self-Supervised Approach for Deterministic Video Depth Forecasting
Sauradip Nag, Nisarg Shah, Anran Qi +1
In this paper we present a novel self-supervised method to anticipate the depth estimate for a future, unobserved real-world urban scene. This work is the first to explore self-sup…
Few-Shot Temporal Action Localization with Query Adaptive Transformer
Sauradip Nag, Xiatian Zhu, Tao Xiang
Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. A…