SOTAVerified

Vision and Language Navigation

Papers

Showing 201223 of 223 papers

TitleStatusHype
Narrowing the Gap between Vision and Action in NavigationCode0
GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language NavigationCode0
Augmented Commonsense Knowledge for Remote Object GroundingCode0
MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language NavigationCode0
A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location CuesCode0
ULN: Towards Underspecified Vision-and-Language NavigationCode0
LOViS: Learning Orientation and Visual Signals for Vision and Language NavigationCode0
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language NavigationCode0
Local Slot Attention for Vision-and-Language NavigationCode0
VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language NavigationCode0
FOAM: A Follower-aware Speaker Model For Vision-and-Language NavigationCode0
Explicit Object Relation Alignment for Vision and Language NavigationCode0
Spatially-Aware Speaker for Vision-and-Language Navigation Instruction GenerationCode0
Speaker-Follower Models for Vision-and-Language NavigationCode0
Chasing Ghosts: Instruction Following as Bayesian State TrackingCode0
Embodied Vision-and-Language Navigation with Dynamic Convolutional FiltersCode0
A Navigation Framework Utilizing Vision-Language ModelsCode0
Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction GenerationCode0
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language NavigationCode0
Diagnosing Vision-and-Language Navigation: What Really MattersCode0
Behavioral Analysis of Vision-and-Language Navigation AgentsCode0
DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive LearningCode0
Into the Unknown: Generating Geospatial Descriptions for New EnvironmentsCode0
Show:102550
← PrevPage 5 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1humansuccess0.86Unverified
2Lilysuccess0.79Unverified
3Airbertsuccess0.78Unverified
4explore@40 beam-searchsuccess0.74Unverified
5Global Normalizationsuccess0.74Unverified
6VLN-Bertsuccess0.73Unverified
7BEVBertsuccess0.73Unverified
8GMapsuccess0.73Unverified
9Gloabl Normalization pre-exploresuccess0.73Unverified
10FOAM-Beam Searchsuccess0.72Unverified
#ModelMetricClaimedVerifiedStatus
1FLAMETask Completion (TC)40.2Unverified
2ORAR + junction type + heading deltaTask Completion (TC)29.1Unverified
3ORARTask Completion (TC)24.2Unverified
4ARC + L2STOPTask Completion (TC)16.68Unverified
5VLN Transformer +M-50 +styleTask Completion (TC)16.2Unverified
6VLN TransformerTask Completion (TC)14.9Unverified
7ARCTask Completion (TC)14.13Unverified
8Retouch-RConcatTask Completion (TC)12.8Unverified
9Gated Attention (GA)Task Completion (TC)11.9Unverified
10RConcatTask Completion (TC)11.8Unverified
#ModelMetricClaimedVerifiedStatus
1MARVALndtw66.76Unverified
2EnvEdit-PTndtw64.61Unverified
3HAMTndtw59.94Unverified
4CLEAR-CLIPndtw53.69Unverified
5Monolingual Baselinendtw41.05Unverified
6Multilingual Baselinendtw36.81Unverified
#ModelMetricClaimedVerifiedStatus
1FLAMETask Completion (TC)52.44Unverified
2ORAR + junction type + heading deltaTask Completion (TC)46.7Unverified
3ORARTask Completion (TC)45.1Unverified
4Gated AttentionTask Completion (TC)17Unverified
5RconcatTask Completion (TC)14.7Unverified
#ModelMetricClaimedVerifiedStatus
1R2R+EnvDropspl0.61Unverified
2RCM + SILspl0.59Unverified
3Tactical Rewind - shortspl0.41Unverified
#ModelMetricClaimedVerifiedStatus
1Hierarchical Cross-Modal AgentSPL (Sucess Weighted by Path Length)0.4Unverified